Dissertations / Theses on the topic 'Réseaux de neuronnes à convolution'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Réseaux de neuronnes à convolution.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Khalfaoui, Hassani Ismail. "Convolution dilatée avec espacements apprenables." Electronic Thesis or Diss., Université de Toulouse (2023-....), 2024. http://www.theses.fr/2024TLSES017.
Full textIn this thesis, we develop and study the Dilated Convolution with Learnable Spacings (DCLS) method. The DCLS method can be considered as an extension of the standard dilated convolution method, but in which the positions of the weights of a neural network are learned during training by the gradient backpropagation algorithm, thanks to an interpolation technique. We empirically demonstrate the effectiveness of the DCLS method by providing concrete evidence from numerous supervised learning experiments. These experiments are drawn from the fields of computer vision, audio, and speech processing, and all show that the DCLS method has a competitive advantage over standard convolution techniques, as well as over several advanced convolution methods. Our approach is structured in several steps, starting with an analysis of the literature and existing convolution techniques that preceded the development of the DCLS method. We were particularly interested in the methods that are closely related to our own and that remain essential to capture the nuances and uniqueness of our approach. The cornerstone of our study is the introduction and application of the DCLS method to convolutional neural networks (CNNs), as well as to hybrid architectures that rely on both convolutional and visual attention approaches. The DCLS method is particularly noteworthy for its capabilities in supervised computer vision tasks such as classification, semantic segmentation, and object detection, all of which are essential tasks in the field. Having originally developed the DCLS method with bilinear interpolation, we explored other interpolation methods that could replace the bilinear interpolation conventionally used in DCLS, and which aim to make the position parameters of the weights in the convolution kernel differentiable. Gaussian interpolation proved to be slightly better in terms of performance. Our research then led us to apply the DCLS method in the field of spiking neural networks (SNNs) to enable synaptic delay learning within a neural network that could eventually be transferred to so-called neuromorphic chips. The results show that the DCLS method stands out as a new state-of-the-art technique in SNN audio classification for certain benchmark tasks in this field. These tasks involve datasets with a high temporal component. In addition, we show that DCLS can significantly improve the accuracy of artificial neural networks for the multi-label audio classification task, a key achievement in one of the most important audio classification benchmarks. We conclude with a discussion of the chosen experimental setup, its limitations, the limitations of our method, and our results
Mamalet, Franck. "Adéquation algorithme-architecture pour les réseaux de neurones à convolution : application à l'analyse de visages embarquée." Thesis, Lyon, INSA, 2011. http://www.theses.fr/2011ISAL0068.
Full textProliferation of image sensors in many electronic devices, and increasing processing capabilities of such sensors, open a field of exploration for the implementation and optimization of complex image processing algorithms in order to provide embedded vision systems. This work is a contribution in the research domain of algorithm-architecture matching. It focuses on a class of algorithms called convolution neural network (ConvNet) and its applications in embedded facial analysis. The facial analysis framework, introduced by Garcia et al., was chosen for its state of the art performances in detection/recognition, and also for its homogeneity based on ConvNets. The first contribution of this work deals with an adequacy study of this facial analysis framework with embedded processors. We propose several algorithmic adaptations of ConvNets, and show that they can lead to significant speedup factors (up to 700) on an embedded processor for mobile phone, without performance degradation. We then present a study of ConvNets parallelization capabilities, through N. Farrugia's PhD work. A coarse-grain parallelism exploration of ConvNets, followed by study of internal scheduling of elementary processors, lead to a parameterized parallel architecture on FPGA, able to detect faces at more than 10 VGA frames per second. Finally, we propose an extension of these studies to the learning phase of neural networks. We analyze several hypothesis space restrictions for ConvNets, and show, on a case study, that classification rate performances are almost the same with a training time divided by up to five
Zossou, Vincent-Béni Sèna. "Détection du carcinome hépatocellulaire et des métastases hépatiques basée sur les images tomodensitométriques et l'apprentissage automatique." Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPASR034.
Full textRadiologists use a series of images from abdominal computed tomography (CT) scans to examine the liver and diagnose potential pathologies. However, this process is often lengthy, complex, and prone to human error. Recent studies have shown that artificial intelligence (AI) has opened new horizons in medical imaging, allowing for earlier detection of liver cancers and optimizing the entire diagnostic process. In Africa, particularly in Benin, few studies have been conducted on the use of these techniques, largely due to a lack of equipment and local data. This thesis addresses this gap by proposing AI techniques for automatically detecting and classifying liver lesions from CT scans. Specifically, it presents a tool that includes: (i) a liver and lesion segmentation model based on a neural network, (ii) a radiomic signature to better characterize liver conditions, (iii) a lesion classification model using convolutional neural networks, and (iv) a diagnostic assistance platform to improve patient care. The results demonstrate improvements over existing solutions, paving the way for broader adoption of these technologies, with the aim of improving healthcare quality and reducing medical errors
Martin, Pierre-Etienne. "Détection et classification fines d'actions à partir de vidéos par réseaux de neurones à convolutions spatio-temporelles : Application au tennis de table." Thesis, Bordeaux, 2020. http://www.theses.fr/2020BORD0313.
Full textAction recognition in videos is one of the key problems in visual data interpretation. Despite intensive research, differencing and recognizing similar actions remains a challenge. This thesis deals with fine-grained classification of sport gestures from videos, with an application to table tennis.In this manuscript, we propose a method based on deep learning for automatically segmenting and classifying table tennis strokes in videos. Our aim is to design a smart system for students and teachers for analyzing their performances. By profiling the players, a teacher can therefore tailor the training sessions more efficiently in order to improve their skills. Players can also have an instant feedback on their performances.For developing such a system with fine-grained classification, a very specific dataset is needed to supervise the learning process. To that aim, we built the “TTStroke-21” dataset, which is composed of 20 stroke classes plus a rejection class. The TTStroke-21 dataset comprises video clips of recorded table tennis exercises performed by students at the sport faculty of the University of Bordeaux - STAPS. These recorded sessions were annotated by professional players or teachers using a crowdsourced annotation platform. The annotations consist in a description of the handedness of the player and information for each stroke performed (starting and ending frames, class of the stroke).Fine-grained action recognition has some notable differences with coarse-grained action recognition. In general, datasets used for coarse-grained action recognition, the background context often provides discriminative information that methods can use to classify the action, rather than focusing on the action itself. In fine-grained classification, where the inter-class similarity is high, discriminative visual features are harder to extract and the motion plays a key role for characterizing an action.In this thesis, we introduce a Twin Spatio-Temporal Convolutional Neural Network. This deep learning network takes as inputs an RGB image sequence and its computed Optical Flow. The RGB image sequence allows our model to capture appearance features while the optical flow captures motion features. Those two streams are processed in parallel using 3D convolutions, and fused at the last stage of the network. Spatio-temporal features extracted in the network allow efficient classification of video clips from TTStroke-21. Our method gets an average classification performance of 87.3% with a best run of 93.2% accuracy on the test set. When applied on joint detection and classification task, the proposed method reaches an accuracy of 82.6%.A systematic study of the influence of each stream and fusion types on classification accuracy has been performed, giving clues on how to obtain the best performances. A comparison of different optical flow methods and the role of their normalization on the classification score is also done. The extracted features are also analyzed by back-tracing strong features from the last convolutional layer to understand the decision path of the trained model. Finally, we introduce an attention mechanism to help the model focusing on particular characteristic features and also to speed up the training process. For comparison purposes, we provide performances of other methods on TTStroke-21 and test our model on other datasets. We notice that models performing well on coarse-grained action datasets do not always perform well on our fine-grained action dataset.The research presented in this manuscript was validated with publications in one international journal, five international conference papers, two international workshop papers and a reconductible task in MediaEval workshop in which participants can apply their action recognition methods to TTStroke-21. Two additional international workshop papers are in process along with one book chapter
Pothier, Dominique. "Réseaux convolutifs à politiques." Master's thesis, Université Laval, 2021. http://hdl.handle.net/20.500.11794/69184.
Full textDespite their excellent performances, artificial neural networks high demand of both data and computational power limit their adoption in many domains. Developing less demanding architecture thus remain an important endeavor. This thesis seeks to produce a more flexible and less resource-intensive architecture by using reinforcement learning theory. When considering a network as an agent instead of a function approximator, one realize that the implicit policy followed by popular feed forward networks is extremely simple. We hypothesize that an architecture able to learn a more flexible policy could reach similar performances while reducing its resource footprint. The architecture we propose is inspired by research done in weight prediction, particularly by the hypernetwork architecture, which we use as a baseline model.Our results show that learning a dynamic policy achieving similar results to the static policies of conventional networks is not a trivial task. Our proposed architecture succeeds in limiting its parameter space by 20%, but does so at the cost of a 24% computation increase and loss of5% accuracy. Despite those results, we believe that this architecture provides a baseline that can be improved in multiple ways that we describe in the conclusion.
Li, Xuhong. "Regularization schemes for transfer learning with convolutional networks." Thesis, Compiègne, 2019. http://www.theses.fr/2019COMP2497/document.
Full textTransfer learning with deep convolutional neural networks significantly reduces the computation and data overhead of the training process and boosts the performance on the target task, compared to training from scratch. However, transfer learning with a deep network may cause the model to forget the knowledge acquired when learning the source task, leading to the so-called catastrophic forgetting. Since the efficiency of transfer learning derives from the knowledge acquired on the source task, this knowledge should be preserved during transfer. This thesis solves this problem of forgetting by proposing two regularization schemes that preserve the knowledge during transfer. First we investigate several forms of parameter regularization, all of which explicitly promote the similarity of the final solution with the initial model, based on the L1, L2, and Group-Lasso penalties. We also propose the variants that use Fisher information as a metric for measuring the importance of parameters. We validate these parameter regularization approaches on various tasks. The second regularization scheme is based on the theory of optimal transport, which enables to estimate the dissimilarity between two distributions. We benefit from optimal transport to penalize the deviations of high-level representations between the source and target task, with the same objective of preserving knowledge during transfer learning. With a mild increase in computation time during training, this novel regularization approach improves the performance of the target tasks, and yields higher accuracy on image classification tasks compared to parameter regularization approaches
Carpentier, Mathieu. "Classification fine par réseau de neurones à convolution." Master's thesis, Université Laval, 2019. http://hdl.handle.net/20.500.11794/35835.
Full textArtificial intelligence is a relatively recent research domain. With it, many breakthroughs were made on a number of problems that were considered very hard. Fine-grained classification is one of those problems. However, a relatively small amount of research has been done on this task even though itcould represent progress on a scientific, commercial and industrial level. In this work, we talk about applying fine-grained classification on concrete problems such as tree bark classification and mould classification in culture. We start by presenting fundamental deep learning concepts at the root of our solution. Then, we present multiple experiments made in order to try to solve the tree bark classification problem and we detail the novel dataset BarkNet 1.0 that we made for this project. With it, we were able to develop a method that obtains an accuracy of 93.88% on singlecrop in a single image, and an accuracy of 97.81% using a majority voting approach on all the images of a tree. We conclude by demonstrating the feasibility of applying our method on new problems by showing two concrete applications on which we tried our approach, industrial tree classification and mould classification.
Chabot, Florian. "Analyse fine 2D/3D de véhicules par réseaux de neurones profonds." Thesis, Université Clermont Auvergne (2017-2020), 2017. http://www.theses.fr/2017CLFAC018/document.
Full textIn this thesis, we are interested in fine-grained analysis of vehicle from an image. We define fine-grained analysis as the following concepts : vehicle detection in the image, vehicle viewpoint (or orientation) estimation, vehicle visibility characterization, vehicle 3D localization and make and model recognition. The design of reliable solutions for fine-grained analysis of vehicle open the door to multiple applications in particular for intelligent transport systems as well as video surveillance systems. In this work, we propose several contributions allowing to address partially or wholly this issue. Proposed approaches are based on joint deep learning technologies and 3D models. In a first section, we deal with make and model classification keeping in mind the difficulty to create training data. In a second section, we investigate a novel method for both vehicle detection and fine-grained viewpoint estimation based on local apparence features and geometric spatial coherence. It uses models learned only on synthetic data. Finally, in a third section, a complete system for fine-grained analysis is proposed. It is based on the multi-task concept. Throughout this report, we provide quantitative and qualitative results. On several aspects related to vehicle fine-grained analysis, this work allowed to outperform state of the art methods
Haj, Hassan Hawraa. "Détection et classification temps réel de biocellules anormales par technique de segmentation d’images." Electronic Thesis or Diss., Université de Lorraine, 2018. http://www.theses.fr/2018LORR0043.
Full textDevelopment of methods for help diagnosis of the real time detection of abnormal cells (which can be considered as cancer cells) through bio-image processing and detection are most important research directions in information science and technology. Our work has been concerned by developing automatic reading procedures of the normal and abnormal bio-images tissues. Therefore, the first step of our work is to detect a certain type of abnormal bio-images associated to many types evolution of cancer within a Microscopic multispectral image, which is an image, repeated in many wavelengths. And using a new segmentation method that reforms itself in an iterative adaptive way to localize and cover the real cell contour, using some segmentation techniques. It is based on color intensity and can be applied on sequences of objects in the image. This work presents a classification of the abnormal tissues using the Convolution neural network (CNN), where it was applied on the microscopic images segmented using the snake method, which gives a high performance result with respect to the other segmentation methods. This classification method reaches high performance values, where it reaches 100% for training and 99.168% for testing. This method was compared to different papers that uses different feature extraction, and proved its high performance with respect to other methods. As a future work, we will aim to validate our approach on a larger datasets, and to explore different CNN architectures and the optimization of the hyper-parameters, in order to increase its performance, and it will be applied to relevant medical imaging tasks including computer-aided diagnosis
Paillassa, Maxime. "Détection robuste de sources astronomiques par réseaux de neurones à convolutions." Thesis, Bordeaux, 2020. http://www.theses.fr/2020BORD0147.
Full textExtracting reliable source catalogs from images is crucial for a broad range of astronomical research topics.However, the efficiency of current source detection methods becomes severely limited in crowded fields, or when images are contaminated by optical, electronic and environmental defects.Performance in terms of reliability and completeness is now often insufficient with regard to the scientific requirements of large imaging surveys.In this thesis, we develop new methods to produce more robust and reliable source catalogs.We leverage recent advances in deep supervised learning to design generic and reliable models based on convolutional neural networks (CNNs).We present MaxiMask and MaxiTrack, two convolutional neural networks that we trained to automatically identify 13 different types of image defects in astronomical exposures.We also introduce a prototype of a multi-scale CNN-based source detector robust to image defects, which we show to significantly outperform existing algorithms.We discuss the current limitations and potential improvements of our approach in the scope of forthcoming large scale surveys such as Euclid
Oquab, Maxime. "Convolutional neural networks : towards less supervision for visual recognition." Thesis, Paris Sciences et Lettres (ComUE), 2018. http://www.theses.fr/2018PSLEE061.
Full textConvolutional Neural Networks are flexible learning algorithms for computer vision that scale particularly well with the amount of data that is provided for training them. Although these methods had successful applications already in the ’90s, they were not used in visual recognition pipelines because of their lesser performance on realistic natural images. It is only after the amount of data and the computational power both reached a critical point that these algorithms revealed their potential during the ImageNet challenge of 2012, leading to a paradigm shift in visual recogntion. The first contribution of this thesis is a transfer learning setup with a Convolutional Neural Network for image classification. Using a pre-training procedure, we show that image representations learned in a network generalize to other recognition tasks, and their performance scales up with the amount of data used in pre-training. The second contribution of this thesis is a weakly supervised setup for image classification that can predict the location of objects in complex cluttered scenes, based on a dataset indicating only with the presence or absence of objects in training images. The third contribution of this thesis aims at finding possible paths for progress in unsupervised learning with neural networks. We study the recent trend of Generative Adversarial Networks and propose two-sample tests for evaluating models. We investigate possible links with concepts related to causality, and propose a two-sample test method for the task of causal discovery. Finally, building on a recent connection with optimal transport, we investigate what these generative algorithms are learning from unlabeled data
Fernandez, Brillet Lucas. "Réseaux de neurones CNN pour la vision embarquée." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM043.
Full textRecently, Convolutional Neural Networks have become the state-of-the-art soluion(SOA) to most computer vision problems. In order to achieve high accuracy rates, CNNs require a high parameter count, as well as a high number of operations. This greatly complicates the deployment of such solutions in embedded systems, which strive to reduce memory size. Indeed, while most embedded systems are typically in the range of a few KBytes of memory, CNN models from the SOA usually account for multiple MBytes, or even GBytes in model size. Throughout this thesis, multiple novel ideas allowing to ease this issue are proposed. This requires to jointly design the solution across three main axes: Application, Algorithm and Hardware.In this manuscript, the main levers allowing to tailor computational complexity of a generic CNN-based object detector are identified and studied. Since object detection requires scanning every possible location and scale across an image through a fixed-input CNN classifier, the number of operations quickly grows for high-resolution images. In order to perform object detection in an efficient way, the detection process is divided into two stages. The first stage involves a region proposal network which allows to trade-off recall for the number of operations required to perform the search, as well as the number of regions passed on to the next stage. Techniques such as bounding box regression also greatly help reduce the dimension of the search space. This in turn simplifies the second stage, since it allows to reduce the task’s complexity to the set of possible proposals. Therefore, parameter counts can greatly be reduced.Furthermore, CNNs also exhibit properties that confirm their over-dimensionment. This over-dimensionement is one of the key success factors of CNNs in practice, since it eases the optimization process by allowing a large set of equivalent solutions. However, this also greatly increases computational complexity, and therefore complicates deploying the inference stage of these algorithms on embedded systems. In order to ease this problem, we propose a CNN compression method which is based on Principal Component Analysis (PCA). PCA allows to find, for each layer of the network independently, a new representation of the set of learned filters by expressing them in a more appropriate PCA basis. This PCA basis is hierarchical, meaning that basis terms are ordered by importance, and by removing the least important basis terms, it is possible to optimally trade-off approximation error for parameter count. Through this method, it is possible to compress, for example, a ResNet-32 network by a factor of ×2 both in the number of parameters and operations with a loss of accuracy <2%. It is also shown that the proposed method is compatible with other SOA methods which exploit other CNN properties in order to reduce computational complexity, mainly pruning, winograd and quantization. Through this method, we have been able to reduce the size of a ResNet-110 from 6.88Mbytes to 370kbytes, i.e. a x19 memory gain with a 3.9 % accuracy loss.All this knowledge, is applied in order to achieve an efficient CNN-based solution for a consumer face detection scenario. The proposed solution consists of just 29.3kBytes model size. This is x65 smaller than other SOA CNN face detectors, while providing equal detection performance and lower number of operations. Our face detector is also compared to a more traditional Viola-Jones face detector, exhibiting approximately an order of magnitude faster computation, as well as the ability to scale to higher detection rates by slightly increasing computational complexity.Both networks are finally implemented in a custom embedded multiprocessor, verifying that theorical and measured gains from PCA are consistent. Furthermore, parallelizing the PCA compressed network over 8 PEs achieves a x11.68 speed-up with respect to the original network running on a single PE
Côté, Marc-Alexandre. "Réseaux de neurones génératifs avec structure." Thèse, Université de Sherbrooke, 2017. http://hdl.handle.net/11143/10489.
Full textEtienne, Caroline. "Apprentissage profond appliqué à la reconnaissance des émotions dans la voix." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLS517.
Full textThis thesis deals with the application of artificial intelligence to the automatic classification of audio sequences according to the emotional state of the customer during a commercial phone call. The goal is to improve on existing data preprocessing and machine learning models, and to suggest a model that is as efficient as possible on the reference IEMOCAP audio dataset. We draw from previous work on deep neural networks for automatic speech recognition, and extend it to the speech emotion recognition task. We are therefore interested in End-to-End neural architectures to perform the classification task including an autonomous extraction of acoustic features from the audio signal. Traditionally, the audio signal is preprocessed using paralinguistic features, as part of an expert approach. We choose a naive approach for data preprocessing that does not rely on specialized paralinguistic knowledge, and compare it with the expert approach. In this approach, the raw audio signal is transformed into a time-frequency spectrogram by using a short-term Fourier transform. In order to apply a neural network to a prediction task, a number of aspects need to be considered. On the one hand, the best possible hyperparameters must be identified. On the other hand, biases present in the database should be minimized (non-discrimination), for example by adding data and taking into account the characteristics of the chosen dataset. We study these aspects in order to develop an End-to-End neural architecture that combines convolutional layers specialized in the modeling of visual information with recurrent layers specialized in the modeling of temporal information. We propose a deep supervised learning model, competitive with the current state-of-the-art when trained on the IEMOCAP dataset, justifying its use for the rest of the experiments. This classification model consists of a four-layer convolutional neural networks and a bidirectional long short-term memory recurrent neural network (BLSTM). Our model is evaluated on two English audio databases proposed by the scientific community: IEMOCAP and MSP-IMPROV. A first contribution is to show that, with a deep neural network, we obtain high performances on IEMOCAP, and that the results are promising on MSP-IMPROV. Another contribution of this thesis is a comparative study of the output values of the layers of the convolutional module and the recurrent module according to the data preprocessing method used: spectrograms (naive approach) or paralinguistic indices (expert approach). We analyze the data according to their emotion class using the Euclidean distance, a deterministic proximity measure. We try to understand the characteristics of the emotional information extracted autonomously by the network. The idea is to contribute to research focused on the understanding of deep neural networks used in speech emotion recognition and to bring more transparency and explainability to these systems, whose decision-making mechanism is still largely misunderstood
Abbasi, Mahdieh. "Toward robust deep neural networks." Doctoral thesis, Université Laval, 2020. http://hdl.handle.net/20.500.11794/67766.
Full textIn this thesis, our goal is to develop robust and reliable yet accurate learning models, particularly Convolutional Neural Networks (CNNs), in the presence of adversarial examples and Out-of-Distribution (OOD) samples. As the first contribution, we propose to predict adversarial instances with high uncertainty through encouraging diversity in an ensemble of CNNs. To this end, we devise an ensemble of diverse specialists along with a simple and computationally efficient voting mechanism to predict the adversarial examples with low confidence while keeping the predictive confidence of the clean samples high. In the presence of high entropy in our ensemble, we prove that the predictive confidence can be upper-bounded, leading to have a globally fixed threshold over the predictive confidence for identifying adversaries. We analytically justify the role of diversity in our ensemble on mitigating the risk of both black-box and white-box adversarial examples. Finally, we empirically assess the robustness of our ensemble to the black-box and the white-box attacks on several benchmark datasets.The second contribution aims to address the detection of OOD samples through an end-to-end model trained on an appropriate OOD set. To this end, we address the following central question: how to differentiate many available OOD sets w.r.t. a given in distribution task to select the most appropriate one, which in turn induces a model with a high detection rate of unseen OOD sets? To answer this question, we hypothesize that the “protection” level of in-distribution sub-manifolds by each OOD set can be a good possible property to differentiate OOD sets. To measure the protection level, we then design three novel, simple, and cost-effective metrics using a pre-trained vanilla CNN. In an extensive series of experiments on image and audio classification tasks, we empirically demonstrate the abilityof an Augmented-CNN (A-CNN) and an explicitly-calibrated CNN for detecting a significantly larger portion of unseen OOD samples, if they are trained on the most protective OOD set. Interestingly, we also observe that the A-CNN trained on the most protective OOD set (calledA-CNN) can also detect the black-box Fast Gradient Sign (FGS) adversarial examples. As the third contribution, we investigate more closely the capacity of the A-CNN on the detection of wider types of black-box adversaries. To increase the capability of A-CNN to detect a larger number of adversaries, we augment its OOD training set with some inter-class interpolated samples. Then, we demonstrate that the A-CNN trained on the most protective OOD set along with the interpolated samples has a consistent detection rate on all types of unseen adversarial examples. Where as training an A-CNN on Projected Gradient Descent (PGD) adversaries does not lead to a stable detection rate on all types of adversaries, particularly the unseen types. We also visually assess the feature space and the decision boundaries in the input space of a vanilla CNN and its augmented counterpart in the presence of adversaries and the clean ones. By a properly trained A-CNN, we aim to take a step toward a unified and reliable end-to-end learning model with small risk rates on both clean samples and the unusual ones, e.g. adversarial and OOD samples.The last contribution is to show a use-case of A-CNN for training a robust object detector on a partially-labeled dataset, particularly a merged dataset. Merging various datasets from similar contexts but with different sets of Object of Interest (OoI) is an inexpensive way to craft a large-scale dataset which covers a larger spectrum of OoIs. Moreover, merging datasets allows achieving a unified object detector, instead of having several separate ones, resultingin the reduction of computational and time costs. However, merging datasets, especially from a similar context, causes many missing-label instances. With the goal of training an integrated robust object detector on a partially-labeled but large-scale dataset, we propose a self-supervised training framework to overcome the issue of missing-label instances in the merged datasets. Our framework is evaluated on a merged dataset with a high missing-label rate. The empirical results confirm the viability of our generated pseudo-labels to enhance the performance of YOLO, as the current (to date) state-of-the-art object detector.
Haj, Hassan Hawraa. "Détection et classification temps réel de biocellules anormales par technique de segmentation d’images." Thesis, Université de Lorraine, 2018. http://www.theses.fr/2018LORR0043.
Full textDevelopment of methods for help diagnosis of the real time detection of abnormal cells (which can be considered as cancer cells) through bio-image processing and detection are most important research directions in information science and technology. Our work has been concerned by developing automatic reading procedures of the normal and abnormal bio-images tissues. Therefore, the first step of our work is to detect a certain type of abnormal bio-images associated to many types evolution of cancer within a Microscopic multispectral image, which is an image, repeated in many wavelengths. And using a new segmentation method that reforms itself in an iterative adaptive way to localize and cover the real cell contour, using some segmentation techniques. It is based on color intensity and can be applied on sequences of objects in the image. This work presents a classification of the abnormal tissues using the Convolution neural network (CNN), where it was applied on the microscopic images segmented using the snake method, which gives a high performance result with respect to the other segmentation methods. This classification method reaches high performance values, where it reaches 100% for training and 99.168% for testing. This method was compared to different papers that uses different feature extraction, and proved its high performance with respect to other methods. As a future work, we will aim to validate our approach on a larger datasets, and to explore different CNN architectures and the optimization of the hyper-parameters, in order to increase its performance, and it will be applied to relevant medical imaging tasks including computer-aided diagnosis
Fourure, Damien. "Réseaux de neurones convolutifs pour la segmentation sémantique et l'apprentissage d'invariants de couleur." Thesis, Lyon, 2017. http://www.theses.fr/2017LYSES056/document.
Full textComputer vision is an interdisciplinary field that investigates how computers can gain a high level of understanding from digital images or videos. In artificial intelligence, and more precisely in machine learning, the field in which this thesis is positioned,computer vision involves extracting characteristics from images and then generalizing concepts related to these characteristics. This field of research has become very popular in recent years, particularly thanks to the results of the convolutional neural networks that form the basis of so-called deep learning methods. Today, neural networks make it possible, among other things, to recognize different objects present in an image, to generate very realistic images or even to beat the champions at the Go game. Their performance is not limited to the image domain, since they are also used in other fields such as natural language processing (e. g. machine translation) or sound recognition. In this thesis, we study convolutional neural networks in order to develop specialized architectures and loss functions for low-level tasks (color constancy) as well as high-level tasks (semantic segmentation). Color constancy, is the ability of the human visual system to perceive constant colours for a surface despite changes in the spectrum of illumination (lighting change). In computer vision, the main approach consists in estimating the color of the illuminant and then suppressing its impact on the perceived color of objects. We approach the task of color constancy with the use of neural networks by developing a new architecture composed of a subsampling operator inspired by traditional methods. Our experience shows that our method makes it possible to obtain competitive performances with the state of the art. Nevertheless, our architecture requires a large amount of training data. In order to partially correct this problem and improve the training of neural networks, we present several techniques for artificial data augmentation. We are also making two contributions on a high-level issue : semantic segmentation. This task, which consists of assigning a semantic class to each pixel of an image, is a challenge in computer vision because of its complexity. On the one hand, it requires many examples of training that are costly to obtain. On the other hand, it requires the adaptation of traditional convolutional neural networks in order to obtain a so-called dense prediction, i. e., a prediction for each pixel present in the input image. To solve the difficulty of acquiring training data, we propose an approach that uses several databases annotated with different labels at the same time. To do this, we define a selective loss function that has the advantage of allowing the training of a convolutional neural network from data from multiple databases. We also developed self-context approach that captures the correlations between labels in different databases. Finally, we present our third contribution : a new convolutional neural network architecture called GridNet specialized for semantic segmentation. Unlike traditional networks, implemented with a single path from the input (image) to the output (prediction), our architecture is implemented as a 2D grid allowing several interconnected streams to operate at different resolutions. In order to exploit all the paths of the grid, we propose a technique inspired by dropout. In addition, we empirically demonstrate that our architecture generalize many of well-known stateof- the-art networks. We conclude with an analysis of the empirical results obtained with our architecture which, although trained from scratch, reveals very good performances, exceeding popular approaches often pre-trained
Gonthier, Nicolas. "Transfer learning of convolutional neural networks for texture synthesis and visual recognition in artistic images." Thesis, université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG024.
Full textIn this thesis, we study the transfer of Convolutional Neural Networks (CNN) trained on natural images to related tasks. We follow two axes: texture synthesis and visual recognition in artworks. The first one consists in synthesizing a new image given a reference sample. Most methods are based on enforcing the Gram matrices of ImageNet-trained CNN features. We develop a multi-resolution strategy to take into account large scale structures. This strategy can be coupled with long-range constraints either through a Fourier frequency constraint, or the use of feature maps autocorrelation. This scheme allows excellent high-resolution synthesis especially for regular textures. We compare our methods to alternatives ones with quantitative and perceptual evaluations. In a second axis, we focus on transfer learning of CNN for artistic image classification. CNNs can be used as off-the-shelf feature extractors or fine-tuned. We illustrate the advantage of the last solution. Second, we use feature visualization techniques, CNNs similarity indexes and quantitative metrics to highlight some characteristics of the fine-tuning process. Another possibility is to transfer a CNN trained for object detection. We propose a simple multiple instance method using off-the-shelf deep features and box proposals, for weakly supervised object detection. At training time, only image-level annotations are needed. We experimentally show the interest of our models on six non-photorealistic
Zotti, Clément. "Réseaux de neurones à convolutions pour la segmentation multi structures d'images par résonance magnétique cardiaque." Mémoire, Université de Sherbrooke, 2018. http://hdl.handle.net/11143/11817.
Full textSuzano, Massa Francisco Vitor. "Mise en relation d'images et de modèles 3D avec des réseaux de neurones convolutifs." Thesis, Paris Est, 2017. http://www.theses.fr/2017PESC1198/document.
Full textThe recent availability of large catalogs of 3D models enables new possibilities for a 3D reasoning on photographs. This thesis investigates the use of convolutional neural networks (CNNs) for relating 3D objects to 2D images.We first introduce two contributions that are used throughout this thesis: an automatic memory reduction library for deep CNNs, and a study of CNN features for cross-domain matching. In the first one, we develop a library built on top of Torch7 which automatically reduces up to 91% of the memory requirements for deploying a deep CNN. As a second point, we study the effectiveness of various CNN features extracted from a pre-trained network in the case of images from different modalities (real or synthetic images). We show that despite the large cross-domain difference between rendered views and photographs, it is possible to use some of these features for instance retrieval, with possible applications to image-based rendering.There has been a recent use of CNNs for the task of object viewpoint estimation, sometimes with very different design choices. We present these approaches in an unified framework and we analyse the key factors that affect performance. We propose a joint training method that combines both detection and viewpoint estimation, which performs better than considering the viewpoint estimation separately. We also study the impact of the formulation of viewpoint estimation either as a discrete or a continuous task, we quantify the benefits of deeper architectures and we demonstrate that using synthetic data is beneficial. With all these elements combined, we improve over previous state-of-the-art results on the Pascal3D+ dataset by a approximately 5% of mean average viewpoint precision.In the instance retrieval study, the image of the object is given and the goal is to identify among a number of 3D models which object it is. We extend this work to object detection, where instead we are given a 3D model (or a set of 3D models) and we are asked to locate and align the model in the image. We show that simply using CNN features are not enough for this task, and we propose to learn a transformation that brings the features from the real images close to the features from the rendered views. We evaluate our approach both qualitatively and quantitatively on two standard datasets: the IKEAobject dataset, and a subset of the Pascal VOC 2012 dataset of the chair category, and we show state-of-the-art results on both of them
Plouet, Erwan. "Convolutional and dynamical spintronic neural networks." Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPASP120.
Full textThis thesis addresses the development of spintronic components for neuromorphic computing, a novel approach aimed at reducing the significant energy consumption of AI applications. The widespread adoption of AI, including very large scale langage models like ChatGPT, has led to increased energy demands, with data centers consuming about 1-2% of global power, and projected to double by 2030. Traditional hardware architectures, which separate memory and processing units, are not well-suited for AI tasks, as neural networks require frequent access to large in-memory parameters, resulting in excessive energy dissipation. Neuromorphic computing, inspired by the human brain, merges memory and processing capabilities in the same device, potentially reducing energy use. Spintronics, which manipulates electron spin rather than charge, offers components that can operate at lower power and provide efficient processing solutions. The thesis is divided into two main parts. The first part focuses on the experimental implementation of a hybrid hardware-software convolutional neural network (CNN) using spintronic components. Spintronic synapses, which operate with radio frequency signals, enable frequency multiplexing to reduce the need for numerous physical connections in neural networks. This research work explores various designs of AMR spin diode-based synapses, each with different specificities, and demonstrates the integration of these synapses into a hardware CNN. A significant achievement was the implementation of a spintronic convolutional layer within a CNN that, when combined with a software fully-connected layer, successfully classified images from the FashionMNIST dataset with an accuracy of 88%, closely matching the performance of the pure software equivalent network. Key findings include the development and precise control of spintronic synapses, the fabrication of synaptic chains for weighted summation in neural networks, and the successful implementation of a hybrid CNN with experimental spintronic components on a complex task. The second part of the thesis explores the use of spintronic nano oscillators (STNOs) for processing time-dependent signals through their transient dynamics. STNOs exhibit nonlinear behaviors that can be utilized for complex tasks like time series classification. A network of simulated STNOs was trained to discriminate between different types of time series, demonstrating superior performance compared to standard reservoir computing methods. We also proposed and evaluated a multilayer network architecture of STNOs for more complex tasks, such as classifying handwritten digits presented pixel-by-pixel. This architecture achieved an average accuracy of 89.83% similar to an equivalent standard continuous time recurrent neural network (CTRNN), indicating the potential of these networks to adapt to various dynamic tasks. Additionally, guidelines were established for matching device dynamics with input timescales, crucial for optimizing performance in networks of dynamic neurons. We demonstrated that multilayer networks of coupled STNOs can be effectively trained via backpropagation through time, highlighting the efficiency and scalability of spintronic neuromorphic computing. This research demonstrated that spintronic networks can be used to implement specific architectures and solve complex tasks. This paves the way for the creation of compact, low-power spintronic neural networks that could be an alternative to AI hardware, offering a sustainable solution to the growing energy demands of AI technologies
Saidane, Zohra. "Reconnaissance de texte dans les images et les vidéos en utilisant les réseaux de neurones à convolutions." Phd thesis, Télécom ParisTech, 2008. http://pastel.archives-ouvertes.fr/pastel-00004685.
Full textJiu, Mingyuan. "Spatial information and end-to-end learning for visual recognition." Thesis, Lyon, INSA, 2014. http://www.theses.fr/2014ISAL0038/document.
Full textIn this thesis, we present our research on visual recognition and machine learning. Two types of visual recognition problems are investigated: action recognition and human body part segmentation problem. Our objective is to combine spatial information such as label configuration in feature space, or spatial layout of labels into an end-to-end framework to improve recognition performance. For human action recognition, we apply the bag-of-words model and reformulate it as a neural network for end-to-end learning. We propose two algorithms to make use of label configuration in feature space to optimize the codebook. One is based on classical error backpropagation. The codewords are adjusted by using gradient descent algorithm. The other is based on cluster reassignments, where the cluster labels are reassigned for all the feature vectors in a Voronoi diagram. As a result, the codebook is learned in a supervised way. We demonstrate the effectiveness of the proposed algorithms on the standard KTH human action dataset. For human body part segmentation, we treat the segmentation problem as classification problem, where a classifier acts on each pixel. Two machine learning frameworks are adopted: randomized decision forests and convolutional neural networks. We integrate a priori information on the spatial part layout in terms of pairs of labels or pairs of pixels into both frameworks in the training procedure to make the classifier more discriminative, but pixelwise classification is still performed in the testing stage. Three algorithms are proposed: (i) Spatial part layout is integrated into randomized decision forest training procedure; (ii) Spatial pre-training is proposed for the feature learning in the ConvNets; (iii) Spatial learning is proposed in the logistical regression (LR) or multilayer perceptron (MLP) for classification
Farabet, Clément. "Analyse sémantique des images en temps-réel avec des réseaux convolutifs." Phd thesis, Université Paris-Est, 2013. http://tel.archives-ouvertes.fr/tel-00965622.
Full textLecomte-Denis, François. "Amélioration des procédures guidées par fluoroscopie à l'aide d'un réseau de neurones pour le recalage déformable des organes." Electronic Thesis or Diss., Strasbourg, 2024. http://www.theses.fr/2024STRAD062.
Full textIn fluoroscopy-guided interventions, the lack of contrast prevents direct visualization of essential anatomical structures.Existing solutions have significant drawbacks: the use of CBCT increases radiation exposure, while contrast agents present toxicity risks for patients.Fluoroscopy to CT registration has the potential to alleviate these issues, but existing literature has primarily focused on respiratory motion compensation.Yet, during interventions, clinicians' actions on organs are an additional source of deformation, rendering these registration approaches ineffective.To address these challenges, we present a real-time 2D-3D deformable registration method tailored to fluoroscopy-guided interventions.Our proposed deep learning approach seamlessly integrates into existing clinical workflows, with minimal training time after preoperative CT scan acquisition.Thanks to our novel domain-agnostic data generation framework, the trained neural network can recover arbitrary deformations, leveraging pose information through its 2D-3D feature backprojection module.Experiments on simulated fluoroscopic images demonstrated our method's ability to provide real-time vessel visualization without contrast agents.On real fluoroscopic images, our method compensates for respiratory motion with a median accuracy of 2.4 mm.These results demonstrate the potential of the proposed method, establishing a foundation for future developments while motivating more comprehensive clinical validation
Yang, Lixuan. "Structuring of image databases for the suggestion of products for online advertising." Thesis, Paris, CNAM, 2017. http://www.theses.fr/2017CNAM1102/document.
Full textThe topic of the thesis is the extraction and segmentation of clothing items from still images using techniques from computer vision, machine learning and image description, in view of suggesting non intrusively to the users similar items from a database of retail products. We firstly propose a dedicated object extractor for dress segmentation by combining local information with a prior learning. A person detector is applied to localize sites in the image that are likely to contain the object. Then, an intra-image two-stage learning process is developed to roughly separate foreground pixels from the background. Finally, the object is finely segmented by employing an active contour algorithm that takes into account the previous segmentation and injects specific knowledge about local curvature in the energy function.We then propose a new framework for extracting general deformable clothing items by using a three stage global-local fitting procedure. A set of template initiates an object extraction process by a global alignment of the model, followed by a local search minimizing a measure of the misfit with respect to the potential boundaries in the neighborhood. The results provided by each template are aggregated, with a global fitting criterion, to obtain the final segmentation.In our latest work, we extend the output of a Fully Convolution Neural Network to infer context from local units(superpixels). To achieve this we optimize an energy function,that combines the large scale structure of the image with the locallow-level visual descriptions of superpixels, over the space of all possiblepixel labellings. In addition, we introduce a novel dataset called RichPicture, consisting of 1000 images for clothing extraction from fashion images.The methods are validated on the public database and compares favorably to the other methods according to all the performance measures considered
Caillault, Emilie. "Architecture et Apprentissage d'un Système Hybride Neuro-Markovien pour la Reconnaissance de l'Écriture Manuscrite En-Ligne." Phd thesis, Université de Nantes, 2005. http://tel.archives-ouvertes.fr/tel-00084061.
Full textBeltzung, Benjamin. "Utilisation de réseaux de neurones convolutifs pour mieux comprendre l’évolution et le développement du comportement de dessin chez les Hominidés." Electronic Thesis or Diss., Strasbourg, 2023. http://www.theses.fr/2023STRAJ114.
Full textThe study of drawing behavior can be highly informative, both cognitively and psychologically, in humans and other primates. However, this wealth of information can also be a challenge to analysis and interpretation, particularly in the absence of explanation or verbalization by the author of the drawing. Indeed, an adult's interpretation of a drawing may not be in line with the artist's original intention. During my thesis, I showed that, although generally regarded as black boxes, convolutional neural networks (CNNs) can provide a better understanding of the drawing behavior. Firstly, by using a CNN to classify drawings of a female orangutan according to their season of production, and highlighting variation in style and content. In addition, an ontogenetic approach was considered to quantify the similarity between productions from different age groups. In the future, more interpretable models and the application of new interpretability methods could be applied to better decipher drawing behavior
Oyallon, Edouard. "Analyzing and introducing structures in deep convolutional neural networks." Thesis, Paris Sciences et Lettres (ComUE), 2017. http://www.theses.fr/2017PSLEE060.
Full textThis thesis studies empirical properties of deep convolutional neural networks, and in particular the Scattering Transform. Indeed, the theoretical analysis of the latter is hard and until now remains a challenge: successive layers of neurons have the ability to produce complex computations, whose nature is still unknown, thanks to learning algorithms whose convergence guarantees are not well understood. However, those neural networks are outstanding tools to tackle a wide variety of difficult tasks, like image classification or more formally statistical prediction. The Scattering Transform is a non-linear mathematical operator whose properties are inspired by convolutional networks. In this work, we apply it to natural images, and obtain competitive accuracies with unsupervised architectures. Cascading a supervised neural networks after the Scattering permits to compete on ImageNet2012, which is the largest dataset of labeled images available. An efficient GPU implementation is provided. Then, this thesis focuses on the properties of layers of neurons at various depths. We show that a progressive dimensionality reduction occurs and we study the numerical properties of the supervised classification when we vary the hyper parameters of the network. Finally, we introduce a new class of convolutional networks, whose linear operators are structured by the symmetry groups of the classification task
Yedroudj, Mehdi. "Steganalysis and steganography by deep learning." Thesis, Montpellier, 2019. http://www.theses.fr/2019MONTS095.
Full textImage steganography is the art of secret communication in order to exchange a secret message. In the other hand, image steganalysis attempts to detect the presence of a hidden message by searching artefacts within an image. For about ten years, the classic approach for steganalysis was to use an Ensemble Classifier fed by hand-crafted features. In recent years, studies have shown that well-designed convolutional neural networks (CNNs) can achieve superior performance compared to conventional machine-learning approaches.The subject of this thesis deals with the use of deep learning techniques for image steganography and steganalysis in the spatialdomain.The first contribution is a fast and very effective convolutional neural network for steganalysis, named Yedroudj-Net. Compared tomodern deep learning based steganalysis methods, Yedroudj-Net can achieve state-of-the-art detection results, but also takes less time to converge, allowing the use of a large training set. Moreover,Yedroudj-Net can easily be improved by using well known add-ons. Among these add-ons, we have evaluated the data augmentation, and the the use of an ensemble of CNN; Both increase our CNN performances.The second contribution is the application of deep learning techniques for steganography i.e the embedding. Among the existing techniques, we focus on the 3-player game approach.We propose an embedding algorithm that automatically learns how to hide a message secretly. Our proposed steganography system is based on the use of generative adversarial networks. The training of this steganographic system is conducted using three neural networks that compete against each other: the embedder, the extractor, and the steganalyzer. For the steganalyzer we use Yedroudj-Net, this for its affordable size, and for the fact that its training does not require the use of any tricks that could increase the computational time.This second contribution defines a research direction, by giving first reflection elements while giving promising first results
Faula, Yannick. "Extraction de caractéristiques sur des images acquises en contexte mobile : Application à la reconnaissance de défauts sur ouvrages d’art." Thesis, Lyon, 2020. http://www.theses.fr/2020LYSEI077.
Full textThe french railway network has a huge infrastructure which is composed of many civil engineering structures. These suffer from degradation of time and traffic and they are subject to a periodic monitoring in order to detect appearance of defects. At the moment, this inspection is mainly done visually by monitoring operators. Several companies test new vectors of photo acquisition like the drone, designed for civil engineering monitoring. In this thesis, the main goal is to develop a system able to detect, localize and save potential defects of the infrastructure. A huge issue is to detect sub-pixel defects like cracks in real time for improving the acquisition. For this task, a local analysis by thresholding is designed for treating large images. This analysis can extract some points of interest (FLASH points: Fast Local Analysis by threSHolding) where a straight line can sneak in. The smart spatial relationship of these points allows to detect and localise fine cracks. The results of the crack detection on concrete degraded surfaces coming from images of infrastructure show better performances in time and robustness than the state-of-art algorithms. Before the detection step, we have to ensure the acquired images have a sufficient quality to make the process. A bad focus or a movement blur are prohibited. We developed a method reusing the preceding computations to assess the quality in real time by extracting Local Binary Pattern (LBP) values. Then, in order to make an acquisition for photogrammetric reconstruction, images have to get a sufficient overlapping. Our algorithm, reusing points of interest of the detection, can make a simple matching between two images without using algorithms as type RANSAC. Our method has invariance in rotation, translation and scale range. After the acquisition, with images with optimal quality, it is possible to exploit methods more expensive in time like convolution neural networks. These are not able to detect cracks in real time but can detect other kinds of damages. However, the lack of data requires the constitution of our database. With approaches of independent classification (classifier SVM one-class), we developed a dynamic system able to evolve in time, detect and then classify the different kinds of damages. No system like ours appears in the literature for the defect detection on civil engineering structure. The implemented works on feature extraction on images for damage detection will be used in other applications as smart vehicle navigation or word spotting
Yang, Lixuan. "Structuring of image databases for the suggestion of products for online advertising." Electronic Thesis or Diss., Paris, CNAM, 2017. http://www.theses.fr/2017CNAM1102.
Full textThe topic of the thesis is the extraction and segmentation of clothing items from still images using techniques from computer vision, machine learning and image description, in view of suggesting non intrusively to the users similar items from a database of retail products. We firstly propose a dedicated object extractor for dress segmentation by combining local information with a prior learning. A person detector is applied to localize sites in the image that are likely to contain the object. Then, an intra-image two-stage learning process is developed to roughly separate foreground pixels from the background. Finally, the object is finely segmented by employing an active contour algorithm that takes into account the previous segmentation and injects specific knowledge about local curvature in the energy function.We then propose a new framework for extracting general deformable clothing items by using a three stage global-local fitting procedure. A set of template initiates an object extraction process by a global alignment of the model, followed by a local search minimizing a measure of the misfit with respect to the potential boundaries in the neighborhood. The results provided by each template are aggregated, with a global fitting criterion, to obtain the final segmentation.In our latest work, we extend the output of a Fully Convolution Neural Network to infer context from local units(superpixels). To achieve this we optimize an energy function,that combines the large scale structure of the image with the locallow-level visual descriptions of superpixels, over the space of all possiblepixel labellings. In addition, we introduce a novel dataset called RichPicture, consisting of 1000 images for clothing extraction from fashion images.The methods are validated on the public database and compares favorably to the other methods according to all the performance measures considered
Mabon, Jules. "Apprentissage de modèles de géométrie stochastique et réseaux de neurones convolutifs. Application à la détection d'objets multiples dans des jeux de données aérospatiales." Electronic Thesis or Diss., Université Côte d'Azur, 2023. http://www.theses.fr/2023COAZ4116.
Full textUnmanned aerial vehicles and low-orbit satellites, including CubeSats, are increasingly used for wide-area surveillance, generating substantial data for processing. Satellite imagery acquisition is susceptible to atmospheric disruptions, occlusions, and limited resolution, resulting in limited visual data for small object detection. However, the objects of interest (e.g., small vehicles) are unevenly distributed in the image: there are some priors on the structure of the configurations.In recent years, convolutional neural network (CNN) models have excelled at extracting information from images, especially texture details. Yet, modeling object interactions requires a significant increase in model complexity and parameters. CNN models generally treat interaction as a post-processing step.In contrast, point processes aim to simultaneously model each point's likelihood in relation to the image (data term) and their interactions (prior term). Most point process models rely on contrast measures (foreground vs. background) for their data terms, which work well with clearly contrasted objects and minimal background clutter. However, small vehicles in satellite images exhibit varying contrast levels and a diverse range of background and false alarm objects.In this PhD thesis, we propose harnessing CNN models information extraction abilities in combination with point process interaction models, using CNN outputs as data terms. Additionally, we introduce a unified method for estimating point process model parameters. Our model demonstrates excellent performance on multiple remote sensing datasets, providing geometric regularization and enhanced noise robustness, all with a minimal parameter footprint
Shahkarami, Abtin. "Complexity reduction over bi-RNN-based Kerr nonlinearity equalization in dual-polarization fiber-optic communications via a CRNN-based approach." Electronic Thesis or Diss., Institut polytechnique de Paris, 2022. http://www.theses.fr/2022IPPAT034.
Full textThe impairments arising from the Kerr nonlinearity in optical fibers limit the achievable information rates in fiber-optic communication. Unlike linear effects, such as chromatic dispersion and polarization-mode dispersion, which can be compensated via relatively simple linear equalization at the receiver, the computational complexity of the conventional nonlinearity mitigation techniques, such as the digital backpropagation, can be substantial. Neural networks have recently attracted attention, in this context, for low-complexity nonlinearity mitigation in fiber-optic communications. This Ph.D. dissertation deals with investigating the recurrent neural networks to efficiently compensate for the nonlinear channel impairments in dual-polarization long-haul fiber-optic transmission. We present a hybrid convolutional recurrent neural network (CRNN) architecture, comprising a convolutional neural network (CNN) -based encoder followed by a recurrent layer working in tandem. The CNN-based encoder represents the shortterm channel memory arising from the chromatic dispersion efficiently, while transitioning the signal to a latent space with fewer relevant features. The subsequent recurrent layer is implemented in the form of a unidirectional vanilla RNN, responsible for capturing the long-range interactions neglected by the CNN encoder. We demonstrate that the proposed CRNN achieves the performance of the state-of-theart equalizers in optical fiber communication, with significantly lower computational complexity depending on the system model. Finally, the performance complexity trade-off is established for a number of models, including multi-layer fully-connected neural networks, CNNs, bidirectional recurrent neural networks, bidirectional long short-term memory (bi-LSTM), bidirectional gated recurrent units, convolutional bi-LSTM models, and the suggested hybrid model
Barhoumi, Amira. "Une approche neuronale pour l’analyse d’opinions en arabe." Thesis, Le Mans, 2020. http://www.theses.fr/2020LEMA1022.
Full textMy thesis is part of Arabic sentiment analysis. Its aim is to determine the global polarity of a given textual statement written in MSA or dialectal arabic. This research area has been subject of numerous studies dealing with Indo-European languages, in particular English. One of difficulties confronting this thesis is the processing of Arabic. In fact, Arabic is a morphologically rich language which implies a greater sparsity : we want to overcome this problem by producing, in a completely automatic way, new arabic specific embeddings. Our study focuses on the use of a neural approach to improve polarity detection, using embeddings. These embeddings have revealed fundamental in various natural languages processing tasks (NLP). Our contribution in this thesis concerns several axis. First, we begin with a preliminary study of the various existing pre-trained word embeddings resources in arabic. These embeddings consider words as space separated units in order to capture semantic and syntactic similarities in the embedding space. Second, we focus on the specifity of Arabic language. We propose arabic specific embeddings that take into account agglutination and morphological richness of Arabic. These specific embeddings have been used, alone and in combined way, as input to neural networks providing an improvement in terms of classification performance. Finally, we evaluate embeddings with intrinsic and extrinsic methods specific to sentiment analysis task. For intrinsic embeddings evaluation, we propose a new protocol introducing the notion of sentiment stability in the embeddings space. We propose also a qualitaive extrinsic analysis of our embeddings by using visualisation methods
Yousef, Yaser. "Routage pour la gestion de l'énergie dans les réseaux de capteurs sans fil." Phd thesis, Université de Haute Alsace - Mulhouse, 2010. http://tel.archives-ouvertes.fr/tel-00590407.
Full textPasdeloup, Bastien. "Extending convolutional neural networks to irregular domains through graph inference." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2017. http://www.theses.fr/2017IMTA0048/document.
Full textThis manuscript sums up our work on extending convolutional neuralnetworks to irregular domains through graph inference. It consists of three main chapters, each giving the details of a part of a methodology allowing the definition of such networks to process signals evolving on graphs with unknown structures.First, graph inference from data is explored, in order to provide a graph modeling the support of the signals to classify. Second, translation operators that preserve neighborhood properties of the vertices are identified on the inferred graph. Third, these translations are used to shift a convolutional kernel on the graph in order to define a convolutional neural network that is adapted to the input data.We have illustrated our methodology on a dataset of images. While not using any particular knowledge on the signals, we have been able to infer a graph that is close to a grid. Translations on this graph resemble Euclidean translations. Therefore, this has allowed us to define an adapted convolutional neural network that is very close what one would obtain when using the information that signals are images. This network, trained on the initial data, has out performed state of the art methods by more than 13 points, while using a very simple and easily improvable architecture.The method we have introduced is a generalization of convolutional neural networks. As a matter of fact, they can be seen as aparticularization of our approach in the case where the graph is a grid. Our work thus opens the way to numerous perspectives, as it provides an efficient way to build networks that are adapted to the data
Vialatte, Jean-Charles. "Convolution et apprentissage profond sur graphes." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2018. http://www.theses.fr/2018IMTA0118/document.
Full textConvolutional neural networks have proven to be the deep learning model that performs best on regularly structured datasets like images or sounds. However, they cannot be applied on datasets with an irregular structure (e.g. sensor networks, citation networks, MRIs). In this thesis, we develop an algebraic theory of convolutions on irregular domains. We construct a family of convolutions that are based on group actions (or, more generally, groupoid actions) that acts on the vertex domain and that have properties that depend on the edges. With the help of these convolutions, we propose extensions of convolutional neural netowrks to graph domains. Our researches lead us to propose a generic formulation of the propagation between layers, that we call the neural contraction. From this formulation, we derive many novel neural network models that can be applied on irregular domains. Through benchmarks and experiments, we show that they attain state-of-the-art performances, and beat them in some cases
Pirovano, Antoine. "Computer-aided diagnosis methods for cervical cancer screening on liquid-based Pap smears using convolutional neural networks : design, optimization and interpretability." Electronic Thesis or Diss., Institut polytechnique de Paris, 2021. http://www.theses.fr/2021IPPAT011.
Full textCervical cancer is the second most important cancer for women after breast cancer. In 2012, the number of cases exceeded 500,000 worldwide, among which half turned to be deadly.Until today, primary cervical cancer screening is performed by a regular visual analysis of cells, sampled by pap-smear by cytopathologists under brightfield microscopy in pathology laboratories. In France, about 5 millions of cervical screening are performed each year and about 90% lead to a negative diagnosis (i.e. no pre-cancerous changes detected). Yet, these analyses under microscope are extremely tedious and time-consuming for cytotechnicians and can require the joint opinion of several experts. This process has an impact on the capacity to tackle this huge amount of cases and to avoid false negatives that are the main cause of treatment delay. The lack of automation and traceability of screening is thus becoming more critical as the number of cyto-pathologists decreases. In that respect, the integration of digital tools in pathology laboratories is becoming a real public health stake for patients and the privileged path for the improvement of these laboratories. Since 2012, deep learning methods have revolutionized the computer vision field, in particular thanks to convolutional neural networks that have been applied successfully to a wide range of applications among which biomedical imaging. Along with it, the whole slide imaging digitization process has opened the opportunity for new efficient computer-aided diagnosis methods and tools. In this thesis, after motivating the medical needs and introducing the state-of-the-art deep learning methods for image processing and understanding, we present our contribution to the field of computer vision tackling cervical cancer screening in the context of liquid-based cytology. Our first contribution consists in proposing a simple regularization constraint for classification model training in the context of ordinal regression tasks (i.e. ordered classes). We prove the advantage of our method on cervical cells classification using Herlev dataset. Furthermore, we propose to rely on explanations from gradient-based explanations to perform weakly-supervised localization and detection of abnormality. Finally, we show how we integrate these methods as a computer-aided tool that could be used to reduce the workload of cytopathologists.The second contribution focuses on whole slide classification and the interpretability of these pipelines. We present in detail the most popular approaches for whole slide classification relying on multiple instance learning, and improve the interpretability in a context of weakly-supervised learning through tile-level feature visualizations and a novel manner of computing explanations of heat-maps. Finally, we apply these methods for cervical cancer screening by using a weakly trained “abnormality” detector for region of interest sampling that guides the training
Strock, Anthony. "Mémoire de travail dans les réseaux de neurones récurrents aléatoires." Thesis, Bordeaux, 2020. http://www.theses.fr/2020BORD0195.
Full textWorking memory can be defined as the ability to temporarily store and manipulate information of any kind.For example, imagine that you are asked to mentally add a series of numbers.In order to accomplish this task, you need to keep track of the partial sum that needs to be updated every time a new number is given.The working memory is precisely what would make it possible to maintain (i.e. temporarily store) the partial sum and to update it (i.e. manipulate).In this thesis, we propose to explore the neuronal implementations of this working memory using a limited number of hypotheses.To do this, we place ourselves in the general context of recurrent neural networks and we propose to use in particular the reservoir computing paradigm.This type of very simple model nevertheless makes it possible to produce dynamics that learning can take advantage of to solve a given task.In this job, the task to be performed is a gated working memory task.The model receives as input a signal which controls the update of the memory.When the door is closed, the model should maintain its current memory state, while when open, it should update it based on an input.In our approach, this additional input is present at all times, even when there is no update to do.In other words, we require our model to be an open system, i.e. a system which is always disturbed by its inputs but which must nevertheless learn to keep a stable memory.In the first part of this work, we present the architecture of the model and its properties, then we show its robustness through a parameter sensitivity study.This shows that the model is extremely robust for a wide range of parameters.More or less, any random population of neurons can be used to perform gating.Furthermore, after learning, we highlight an interesting property of the model, namely that information can be maintained in a fully distributed manner, i.e. without being correlated to any of the neurons but only to the dynamics of the group.More precisely, working memory is not correlated with the sustained activity of neurons, which has nevertheless been observed for a long time in the literature and recently questioned experimentally.This model confirms these results at the theoretical level.In the second part of this work, we show how these models obtained by learning can be extended in order to manipulate the information which is in the latent space.We therefore propose to consider conceptors which can be conceptualized as a set of synaptic weights which constrain the dynamics of the reservoir and direct it towards particular subspaces; for example subspaces corresponding to the maintenance of a particular value.More generally, we show that these conceptors can not only maintain information, they can also maintain functions.In the case of mental arithmetic mentioned previously, these conceptors then make it possible to remember and apply the operation to be carried out on the various inputs given to the system.These conceptors therefore make it possible to instantiate a procedural working memory in addition to the declarative working memory.We conclude this work by putting this theoretical model into perspective with respect to biology and neurosciences
Tang, Yuxing. "Weakly supervised learning of deformable part models and convolutional neural networks for object detection." Thesis, Lyon, 2016. http://www.theses.fr/2016LYSEC062/document.
Full textIn this dissertation we address the problem of weakly supervised object detection, wherein the goal is to recognize and localize objects in weakly-labeled images where object-level annotations are incomplete during training. To this end, we propose two methods which learn two different models for the objects of interest. In our first method, we propose a model enhancing the weakly supervised Deformable Part-based Models (DPMs) by emphasizing the importance of location and size of the initial class-specific root filter. We first compute a candidate pool that represents the potential locations of the object as this root filter estimate, by exploring the generic objectness measurement (region proposals) to combine the most salient regions and “good” region proposals. We then propose learning of the latent class label of each candidate window as a binary classification problem, by training category-specific classifiers used to coarsely classify a candidate window into either a target object or a non-target class. Furthermore, we improve detection by incorporating the contextual information from image classification scores. Finally, we design a flexible enlarging-and-shrinking post-processing procedure to modify the DPMs outputs, which can effectively match the approximate object aspect ratios and further improve final accuracy. Second, we investigate how knowledge about object similarities from both visual and semantic domains can be transferred to adapt an image classifier to an object detector in a semi-supervised setting on a large-scale database, where a subset of object categories are annotated with bounding boxes. We propose to transform deep Convolutional Neural Networks (CNN)-based image-level classifiers into object detectors by modeling the differences between the two on categories with both image-level and bounding box annotations, and transferring this information to convert classifiers to detectors for categories without bounding box annotations. We have evaluated both our approaches extensively on several challenging detection benchmarks, e.g. , PASCAL VOC, ImageNet ILSVRC and Microsoft COCO. Both our approaches compare favorably to the state-of-the-art and show significant improvement over several other recent weakly supervised detection methods
Estienne, Théo. "Deep learning-based methods for 3D medical image registration." Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG055.
Full textThis thesis focuses on new deep learning approaches to find the best displacement between two different medical images. This research area, called image registration, have many applications in the clinical pipeline, including the fusion of different imaging types or the temporal follow-up of a patient. This field is studied for many years with various methods, such as diffeomorphic, graph-based or physical-based methods. Recently, deep learning-based methods were proposed using convolutional neural networks.These methods obtained similar results to non-deep learning methods while greatly reducing the computation time and enabling real-time prediction. This improvement comes from the use of graphics processing units (GPU) and a prediction phase where no optimisation is required. However, deep learning-based registration has several limitations, such as the need for large databases to train the network or tuning regularisation hyperparameters to prevent too noisy transformations.In this manuscript, we investigate diverse modifications to deep learning algorithms, working on various imaging types and body parts. We study first the combination of segmentation and registration tasks proposing a new joint architecture. We apply to brain MRI datasets, exploring different cases : brain without and with tumours. Our architecture comprises one encoder and two decoders and the coupling is reinforced by the introduction of a supplementary loss. In the presence of tumour, the similarity loss is modified such as the registration focus only on healthy part ignoring the tumour. Then, we shift to abdominal CT, a more challenging localisation, as there are natural organ's movement and deformation. We improve registration performances thanks to the use of pre-training and pseudo segmentations, the addition of new losses to provide a better regularisation and a multi-steps strategy. Finally, we analyse the explainability of registration networks using a linear decomposition and applying to lung and hippocampus MR. Thanks to our late fusion strategy, we project images to the latent space and calculate a new basis. This basis correspond to elementary transformation witch we study qualitatively
Papadopoulos, Georgios. "Towards a 3D building reconstruction using spatial multisource data and computational intelligence techniques." Thesis, Limoges, 2019. http://www.theses.fr/2019LIMO0084/document.
Full textBuilding reconstruction from aerial photographs and other multi-source urban spatial data is a task endeavored using a plethora of automated and semi-automated methods ranging from point processes, classic image processing and laser scanning. In this thesis, an iterative relaxation system is developed based on the examination of the local context of each edge according to multiple spatial input sources (optical, elevation, shadow & foliage masks as well as other pre-processed data as elaborated in Chapter 6). All these multisource and multiresolution data are fused so that probable line segments or edges are extracted that correspond to prominent building boundaries.Two novel sub-systems have also been developed in this thesis. They were designed with the purpose to provide additional, more reliable, information regarding building contours in a future version of the proposed relaxation system. The first is a deep convolutional neural network (CNN) method for the detection of building borders. In particular, the network is based on the state of the art super-resolution model SRCNN (Dong C. L., 2015). It accepts aerial photographs depicting densely populated urban area data as well as their corresponding digital elevation maps (DEM). Training is performed using three variations of this urban data set and aims at detecting building contours through a novel super-resolved heteroassociative mapping. Another innovation of this approach is the design of a modified custom loss layer named Top-N. In this variation, the mean square error (MSE) between the reconstructed output image and the provided ground truth (GT) image of building contours is computed on the 2N image pixels with highest values . Assuming that most of the N contour pixels of the GT image are also in the top 2N pixels of the re-construction, this modification balances the two pixel categories and improves the generalization behavior of the CNN model. It is shown in the experiments, that the Top-N cost function offers performance gains in comparison to standard MSE. Further improvement in generalization ability of the network is achieved by using dropout.The second sub-system is a super-resolution deep convolutional network, which performs an enhanced-input associative mapping between input low-resolution and high-resolution images. This network has been trained with low-resolution elevation data and the corresponding high-resolution optical urban photographs. Such a resolution discrepancy between optical aerial/satellite images and elevation data is often the case in real world applications. More specifically, low-resolution elevation data augmented by high-resolution optical aerial photographs are used with the aim of augmenting the resolution of the elevation data. This is a unique super-resolution problem where it was found that many of -the proposed general-image SR propositions do not perform as well. The network aptly named building super resolution CNN (BSRCNN) is trained using patches extracted from the aforementioned data. Results show that in comparison with a classic bicubic upscale of the elevation data the proposed implementation offers important improvement as attested by a modified PSNR and SSIM metric. In comparison, other proposed general-image SR methods performed poorer than a standard bicubic up-scaler.Finally, the relaxation system fuses together all these multisource data sources comprising of pre-processed optical data, elevation data, foliage masks, shadow masks and other pre-processed data in an attempt to assign confidence values to each pixel belonging to a building contour. Confidence is augmented or decremented iteratively until the MSE error fails below a specified threshold or a maximum number of iterations have been executed. The confidence matrix can then be used to extract the true building contours via thresholding
Caye, Daudt Rodrigo. "Convolutional neural networks for change analysis in earth observation images with noisy labels and domain shifts." Electronic Thesis or Diss., Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAT033.
Full textThe analysis of satellite and aerial Earth observation images allows us to obtain precise information over large areas. A multitemporal analysis of such images is necessary to understand the evolution of such areas. In this thesis, convolutional neural networks are used to detect and understand changes using remote sensing images from various sources in supervised and weakly supervised settings. Siamese architectures are used to compare coregistered image pairs and to identify changed pixels. The proposed method is then extended into a multitask network architecture that is used to detect changes and perform land cover mapping simultaneously, which permits a semantic understanding of the detected changes. Then, classification filtering and a novel guided anisotropic diffusion algorithm are used to reduce the effect of biased label noise, which is a concern for automatically generated large-scale datasets. Weakly supervised learning is also achieved to perform pixel-level change detection using only image-level supervision through the usage of class activation maps and a novel spatial attention layer. Finally, a domain adaptation method based on adversarial training is proposed, which succeeds in projecting images from different domains into a common latent space where a given task can be performed. This method is tested not only for domain adaptation for change detection, but also for image classification and semantic segmentation, which proves its versatility
Al, Hajj Hassan. "Video analysis for augmented cataract surgery." Thesis, Brest, 2018. http://www.theses.fr/2018BRES0041/document.
Full textThe digital era is increasingly changing the world due to the sheer volume of data produced every day. The medical domain is highly affected by this revolution, because analysing this data can be a source of education/support for the clinicians. In this thesis, we propose to reuse the surgery videos recorded in the operating rooms for computer-assisted surgery system. We are chiefly interested in recognizing the surgical gesture being performed at each instant in order to provide relevant information. To achieve this goal, this thesis addresses the surgical tool recognition problem, with applications in cataract surgery. The main objective of this thesis is to address the surgical tool recognition problem in cataract surgery videos.In the surgical field, those tools are partially visible in videos and highly similar to one another. To address the visual challenges in the cataract surgical field, we propose to add an additional camera filming the surgical tray. Our goal is to detect the tool presence in the two complementary types of videos: tool-tissue interaction and surgical tray videos. The former records the patient's eye and the latter records the surgical tray activities.Two tasks are proposed to perform the task on the surgical tray videos: tools change detection and tool presence detection.First, we establish a similar pipeline for both tasks. It is based on standard classification methods on top of visual learning features. It yields satisfactory results for the tools change task, howev-lateer, it badly performs the surgical tool presence task on the tray. Second, we design deep learning architectures for the surgical tool detection on both video types in order to address the difficulties in manually designing the visual features.To alleviate the inherent challenges on the surgical tray videos, we propose to generate simulated surgical tray scenes along with a patch-based convolutional neural network (CNN).Ultimately, we study the temporal information using RNN processing the CNN results. Contrary to our primary hypothesis, the experimental results show deficient results for surgical tool presence on the tray but very good results on the tool-tissue interaction videos. We achieve even better results in the surgical field after fusing the tool change information coming from the tray and tool presence signals on the tool-tissue interaction videos
Antipov, Grigory. "Apprentissage profond pour la description sémantique des traits visuels humains." Thesis, Paris, ENST, 2017. http://www.theses.fr/2017ENST0071/document.
Full textThe recent progress in artificial neural networks (rebranded as deep learning) has significantly boosted the state-of-the-art in numerous domains of computer vision. In this PhD study, we explore how deep learning techniques can help in the analysis of gender and age from a human face. In particular, two complementary problem settings are considered: (1) gender/age prediction from given face images, and (2) synthesis and editing of human faces with the required gender/age attributes.Firstly, we conduct a comprehensive study which results in an empirical formulation of a set of principles for optimal design and training of gender recognition and age estimation Convolutional Neural Networks (CNNs). As a result, we obtain the state-of-the-art CNNs for gender/age prediction according to the three most popular benchmarks, and win an international competition on apparent age estimation. On a very challenging internal dataset, our best models reach 98.7% of gender classification accuracy and an average age estimation error of 4.26 years.In order to address the problem of synthesis and editing of human faces, we design and train GA-cGAN, the first Generative Adversarial Network (GAN) which can generate synthetic faces of high visual fidelity within required gender and age categories. Moreover, we propose a novel method which allows employing GA-cGAN for gender swapping and aging/rejuvenation without losing the original identity in synthetic faces. Finally, in order to show the practical interest of the designed face editing method, we apply it to improve the accuracy of an off-the-shelf face verification software in a cross-age evaluation scenario
Chen, Dexiong. "Modélisation de données structurées avec des machines profondes à noyaux et des applications en biologie computationnelle." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM070.
Full textDeveloping efficient algorithms to learn appropriate representations of structured data, including sequences or graphs, is a major and central challenge in machine learning. To this end, deep learning has become popular in structured data modeling. Deep neural networks have drawn particular attention in various scientific fields such as computer vision, natural language understanding or biology. For instance, they provide computational tools for biologists to possibly understand and uncover biological properties or relationships among macromolecules within living organisms. However, most of the success of deep learning methods in these fields essentially relies on the guidance of empirical insights as well as huge amounts of annotated data. Exploiting more data-efficient models is necessary as labeled data is often scarce.Another line of research is kernel methods, which provide a systematic and principled approach for learning non-linear models from data of arbitrary structure. In addition to their simplicity, they exhibit a natural way to control regularization and thus to avoid overfitting.However, the data representations provided by traditional kernel methods are only defined by simply designed hand-crafted features, which makes them perform worse than neural networks when enough labeled data are available. More complex kernels inspired by prior knowledge used in neural networks have thus been developed to build richer representations and thus bridge this gap. Yet, they are less scalable. By contrast, neural networks are able to learn a compact representation for a specific learning task, which allows them to retain the expressivity of the representation while scaling to large sample size.Incorporating complementary views of kernel methods and deep neural networks to build new frameworks is therefore useful to benefit from both worlds.In this thesis, we build a general kernel-based framework for modeling structured data by leveraging prior knowledge from classical kernel methods and deep networks. Our framework provides efficient algorithmic tools for learning representations without annotations as well as for learning more compact representations in a task-driven way. Our framework can be used to efficiently model sequences and graphs with simple interpretation of predictions. It also offers new insights about designing more expressive kernels and neural networks for sequences and graphs
Monjoly, Stéphanie. "Outils de prédiction pour la production d’électricité d’origine éolienne : application à l’optimisation du couplage aux réseaux de distributions d’électricité." Thesis, Antilles-Guyane, 2013. http://www.theses.fr/2013AGUY0679/document.
Full textThe high variability of the wind speed has for conse quences that the energy produced by a wind farm is not constant over time. Therefore, the manager can't size the electrical network by takin g into account this type of production. One solution advocated for the development of wind energy and its integrati on with greater security at network, is to develop and improve fore casting tools. The thesi s objective is to improve the performance of a predi ction tool based on Bayesian neural networks, allowing the predi ction of wind power for short timescales. The predictor works, in part icular by the adjustment of parameters, sorne is determined "automatically" through the mechan ism of neural networks Bayesian other , which we cali temporal parameters are at the discretion of the user. The work involves establishing a protocol for the determination of these parameters and improving the performance of the predictor. So, we decided to condition their values depending on the sequence variability of wind power previous the moment of the forecast. First we classified sequences of power according to their coefficients of variation using the method of fuzzy C-means. Then, each formed class was tested for several parameters values, the values associated with the best predictions were selected. Finally , these result s coupled with the formalism of Markov chains , through the transition matrix allowed to obtain rates of improvement over the persistence ranging from 7.73 to 23.22 % depending on the prediction horizon considered
Antipov, Grigory. "Apprentissage profond pour la description sémantique des traits visuels humains." Electronic Thesis or Diss., Paris, ENST, 2017. http://www.theses.fr/2017ENST0071.
Full textThe recent progress in artificial neural networks (rebranded as deep learning) has significantly boosted the state-of-the-art in numerous domains of computer vision. In this PhD study, we explore how deep learning techniques can help in the analysis of gender and age from a human face. In particular, two complementary problem settings are considered: (1) gender/age prediction from given face images, and (2) synthesis and editing of human faces with the required gender/age attributes.Firstly, we conduct a comprehensive study which results in an empirical formulation of a set of principles for optimal design and training of gender recognition and age estimation Convolutional Neural Networks (CNNs). As a result, we obtain the state-of-the-art CNNs for gender/age prediction according to the three most popular benchmarks, and win an international competition on apparent age estimation. On a very challenging internal dataset, our best models reach 98.7% of gender classification accuracy and an average age estimation error of 4.26 years.In order to address the problem of synthesis and editing of human faces, we design and train GA-cGAN, the first Generative Adversarial Network (GAN) which can generate synthetic faces of high visual fidelity within required gender and age categories. Moreover, we propose a novel method which allows employing GA-cGAN for gender swapping and aging/rejuvenation without losing the original identity in synthetic faces. Finally, in order to show the practical interest of the designed face editing method, we apply it to improve the accuracy of an off-the-shelf face verification software in a cross-age evaluation scenario
Guerre, Alexandre. "Champ visuel augmenté pour l'exploration vidéo de la rétine." Thesis, Brest, 2019. http://www.theses.fr/2019BRES0110.
Full textThe main objective of this thesis is toincrease the visual comfort of theophthalmologists during examinations orsurgeries. To do so, we decided toartificially increase in real time the field ofview in videos of retinal exploration. Thetools used for the acquisition of thesevideos are the slit lamp and theendoscope. The increase of the field ofview passes by the establishment ofdynamic 3D maps of the retina.To our knowledge, there is still no suchmethod in the state of the art.In order to implement our solution, westudied the different methods of motionestimations between two images. Wegrouped them into "classical" methods, onthe one hand, including methods based onSIFT or SURF algorithms. On the otherhand, we grouped deep learning methods(or "CNN" methods for ConvolutionalNeural Network).Some of these methods, such as thoseusing FlowNet networks, required groundtruth annotation of movement betweenimages.Since such bases are very difficult to set upin the medical field and do not exist inophthalmology, general databases havebeen used. In addition, we built twodatabases of artificial displacements whichbackgrounds are composed of images ofretinas. Finally, to get around this problemof annotations, a self-supervised deeplearning approach was studied.After comparing the results, it appears thatmethods using convolutional neuralnetworks outperform conventional methodsfor estimating movements in retinal videos.Moreover, only a strong supervision allowsacceptable results. In the future, we hopethat this work will enable surgeons to bemore confident and effective inenvironments where it is sometimesdifficult to find their bearings