Sommaire
Littérature scientifique sur le sujet « Apprentissage par métrique »
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les listes thématiques d’articles de revues, de livres, de thèses, de rapports de conférences et d’autres sources académiques sur le sujet « Apprentissage par métrique ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Thèses sur le sujet "Apprentissage par métrique"
Bhattarai, Binod. « Développement de méthodes de rapprochement physionomique par apprentissage machine ». Caen, 2016. https://hal.archives-ouvertes.fr/tel-01467985.
Texte intégralThe work presented in this PhD thesis takes place in the general context of face matching. More precisely, our goal is to design and develop novel algorithms to learn compact, discriminative, domain invariant or de-identifying representations of faces. Searching and indexing faces open the door to many interesting applications. However, this is made day after day more challenging due to the rapid growth of the volume of faces to analyse. Representing faces by compact and discriminative features is consequently es- sential to deal with such very large datasets. Moreover, this volume is increasing without any apparent limits; this is why it is also relevant to propose solutions to organise faces in meaningful ways, in order to reduce the search space and improve efficiency of the retrieval. Although the volume of faces available on the internet is increasing, it is still difficult to find annotated examples to train models for each possible use cases e. G. For different races, sexes, etc. For every specifie task. Learning a model with training examples from a group of people can fail to predict well in another group due to the uneven rate of changes of biometrie dimensions e. G. , ageing, among them. Similarly, a modellean1ed from a type of feature can fail to make good predictions when tested with another type of feature. It would be ideal to have models producing face representations that would be invariant to these discrepancies. Learning common representations ultimately helps to reduce the domain specifie parameters and, more important!y, allows to use training examples from domains weil represented to other demains. Hence, there is a need for designing algorithms to map the features from different domains to a common subspace -bringing faces bearing same properties closer. On the other band, as automatic face matching tools are getting smarter and smarter, there is an increasing threat on privacy. The popularity in photo sharing on the social networks has exacerbated this risk. In such a context, altering the representations of faces so that the faces cannot be identified by automatic face matchers -while the faces look as similar as before -has become an interesting perspective toward privacy protection. It allows users to limit the risk of sharing their photos in social networks. In ali these scenarios, we explored how the use of Metric Leaming methods as weil as those of Deep Learning can help us to leam compact and discriminative representations of faces. We build on these tools, proposing compact, discriminative, domain invariant representations and de-identifying representations of faces crawled from Flicker. Corn to LFW and generated a novel and more challenging dataset to evaluate our algorithms in large-scale. We applied the proposed methods on a wide range of facial analysing applications. These applications include: large-scale face retrieval, age estimation, attribute predictions and identity de-identification. We have evaluated our algorithms on standard and challenging public datasets such as: LFW, CelebA, MORPH II etc. Moreover, we appended lM faces crawled from Flicker. Corn to LFW and generated a novel and more challenging dataset to evaluate our algorithms in large-scale. Our experiments show that the proposed methods are more accurate and more efficient than compared competitive baselines and existing state-of-art methods, and attain new state-of-art performance
Do, Cao Tri. « Apprentissage de métrique temporelle multi-modale et multi-échelle pour la classification robuste de séries temporelles par plus proches voisins ». Thesis, Université Grenoble Alpes (ComUE), 2016. http://www.theses.fr/2016GREAM028/document.
Texte intégralThe definition of a metric between time series is inherent to several data analysis and mining tasks, including clustering, classification or forecasting. Time series data present naturally several characteristics, called modalities, covering their amplitude, behavior or frequential spectrum, that may be expressed with varying delays and at different temporal granularity and localization - exhibited globally or locally. Combining several modalities at multiple temporal scales to learn a holistic metric is a key challenge for many real temporal data applications. This PhD proposes a Multi-modal and Multi-scale Temporal Metric Learning (M2TML) approach for robust time series nearest neighbors classification. The solution is based on the embedding of pairs of time series into a pairwise dissimilarity space, in which a large margin optimization process is performed to learn the metric. The M2TML solution is proposed for both linear and non linear contexts, and is studied for different regularizers. A sparse and interpretable variant of the solution shows the ability of the learned temporal metric to localize accurately discriminative modalities as well as their temporal scales.A wide range of 30 public and challenging datasets, encompassing images, traces and ECG data, that are linearly or non linearly separable, are used to show the efficiency and the potential of M2TML for time series nearest neighbors classification
Law, Marc Teva. « Distance metric learning for image and webpage comparison ». Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066019/document.
Texte intégralThis thesis focuses on distance metric learning for image and webpage comparison. Distance metrics are used in many machine learning and computer vision contexts such as k-nearest neighbors classification, clustering, support vector machine, information/image retrieval, visualization etc. In this thesis, we focus on Mahalanobis-like distance metric learning where the learned model is parametered by a symmetric positive semidefinite matrix. It learns a linear tranformation such that the Euclidean distance in the induced projected space satisfies learning constraints.First, we propose a method based on comparison between relative distances that takes rich relations between data into account, and exploits similarities between quadruplets of examples. We apply this method on relative attributes and hierarchical image classification. Second, we propose a new regularization method that controls the rank of the learned matrix, limiting the number of independent parameters and overfitting. We show the interest of our method on synthetic and real-world recognition datasets. Eventually, we propose a novel Webpage change detection framework in a context of archiving. For this purpose, we use temporal distance relations between different versions of a same Webpage. The metric learned in a totally unsupervised way detects important regions and ignores unimportant content such as menus and advertisements. We show the interest of our method on different Websites
Leclerc, Sarah Marie-Solveig. « Automatisation de la segmentation sémantique de structures cardiaques en imagerie ultrasonore par apprentissage supervisé ». Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEI121.
Texte intégralThe analysis of medical images plays a critical role in cardiology. Ultrasound imaging, as a real-time, low cost and bed side applicable modality, is nowadays the most commonly used image modality to monitor patient status and perform clinical cardiac diagnosis. However, the semantic segmentation (i.e the accurate delineation and identification) of heart structures is a difficult task due to the low quality of ultrasound images, characterized in particular by the lack of clear boundaries. To compensate for missing information, the best performing methods before this thesis relied on the integration of prior information on cardiac shape or motion, which in turns reduced the adaptability of the corresponding methods. Furthermore, such approaches require man- ual identifications of key points to be adapted to a given image, which makes the full process difficult to reproduce. In this thesis, we propose several original fully-automatic algorithms for the semantic segmentation of echocardiographic images based on supervised learning ap- proaches, where the resolution of the problem is automatically set up using data previously analyzed by trained cardiologists. From the design of a dedicated dataset and evaluation platform, we prove in this project the clinical applicability of fully-automatic supervised learning methods, in particular deep learning methods, as well as the possibility to improve the robustness by incorporating in the full process the prior automatic detection of regions of interest
Nagorny, Pierre. « Contrôle automatique non-invasif de la qualité des produits : Application au procédé d'injection-moulage des thermoplastiques ». Thesis, Chambéry, 2020. http://www.theses.fr/2020CHAMA008.
Texte intégralInline quality control of the product is an important objective for industries growth. Controlling a product quality requires measurements of its quality characteristics. One hundred percent control is an important objective to overcome the limits of the control by sampling, in the case of defects related to exceptional causes. However, industrial constraints have limited the deployment of measurement of product characteristics directly within production lines. Human visual control is limited by its duration incompatible with the production cycle at high speed productions, by its cost and its variability. Computer vision systems present a cost that reserves them for productions with high added value. In addition, the automatic control of the quality of the appearance of the products remains an open research topic.Our work aims to meet these constraints, as part of the injection-molding process of thermoplastics. We propose a control system that is non-invasive for the production process. Parts are checked right out of the injection molding machine.We will study the contribution of non-conventional imaging. Thermography of a hot molded part provides information on its geometry, which is complementary to conventional imaging. Polarimetry makes it possible to discriminate curvature defects of surfaces that change the polarization angle of reflected light and defects in the structure of the material that diffuse light.Furthermore, specifications on products are more and more tighter. Specifications include complex geometric features, as well as appearance features, which are difficult to formalize. However, the appearance characteristics are difficult to formalize. To automate aspect control, it is necessary to model the notion of quality of a part. In order to exploit the measurements made on the hot parts, our approach uses statistical learning methods. Thus, the human expert who knows the notion of quality of a piece transmits his knowledge to the system, by the annotation of a set of learning data. Our control system then learns a metric of the quality of a part, from raw data from sensors. We favor a deep convolutional network approach (Deep Learning) in order to obtain the best performances in fairness of discrimination of the compliant parts. The small amount of annotated samples available in our industrial context has led us to use domain transfer learning methods.Finally, in order to meet all the constraints and validate our propositions, we realized the vertical integration of a prototype of device of measure of the parts and the software solution of treatment by statistical learning. The device integrates thermal imaging, polarimetric imaging, lighting and the on-board processing system necessary for sending data to a remote analysis server.Two application cases make it possible to evaluate the performance and viability of the proposed solution
Boutaleb, Mohamed Yasser. « Egocentric Hand Activity Recognition : The principal components of an egocentric hand activity recognition framework, exploitable for augmented reality user assistance ». Electronic Thesis or Diss., CentraleSupélec, 2022. http://www.theses.fr/2022CSUP0007.
Texte intégralHumans use their hands for various tasks in daily life and industry, making research in this area a recent focus of significant interest. Moreover, analyzing and interpreting human behavior using visual signals is one of the most animated and explored areas of computer vision. With the advent of new augmented reality technologies, researchers are increasingly interested in hand activity understanding from a first-person perspective exploring its suitability for human guidance and assistance. Our work is based on machine learning technology to contribute to this research area. Recently, deep neural networks have proven their outstanding effectiveness in many research areas, allowing researchers to jump significantly in efficiency and robustness.This thesis's main objective is to propose a user's activity recognition framework including four key components, which can be used to assist users during their activities oriented towards specific objectives: industry 4.0 (e.g., assisted assembly, maintenance) and teaching. Thus, the system observes the user's hands and the manipulated objects from the user's viewpoint to recognize his performed hand activity. The desired framework must robustly recognize the user's usual activities. Nevertheless, it must detect unusual ones to feedback and prevent him from performing wrong maneuvers, a fundamental requirement for user assistance. This thesis, therefore, combines techniques from the research fields of computer vision and machine learning to propose comprehensive hand activity recognition components essential for a complete assistance tool
Mignon, Alexis. « Apprentissage de métriques et méthodes à noyaux appliqués à la reconnaissance de personnes dans les images ». Caen, 2012. http://www.theses.fr/2012CAEN2048.
Texte intégralOur work is devoted to person recognition in video images and focuses mainly on faces. We are interested in the registration and recognition steps, assuming that the locations of faces in the images are known. The registration step aims at compensating the location and pose variations of the faces, making them easier to compare. We present a method to predict the location of key-points based on sparse regression. It predicts the offset between average and real positions of a key-point from the appearence of the image around the average positions. Our contributions to face recognition rely on the idea that two different representations of faces of the same person should be closer, with respect to a given distance measure, than those of two different persons. We propose a metric learning method that verifies these properties. Besides, the approach is general enough to be able to learn a distance between different modalities. The models we use in our approaches are linear. To alleviate this limitation, they are extended to the non-linear case through the use of the kernel trick. A part of this thesis precisely deals with the properties of additive homogeneous kernels, well adapted for histogram comparisons. We especially present some oringal theoretical results on the feature map of the power mean kernel
Cuan, Bonan. « Deep similarity metric learning for multiple object tracking ». Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEI065.
Texte intégralMultiple object tracking, i.e. simultaneously tracking multiple objects in the scene, is an important but challenging visual task. Objects should be accurately detected and distinguished from each other to avoid erroneous trajectories. Since remarkable progress has been made in object detection field, “tracking-by-detection” approaches are widely adopted in multiple object tracking research. Objects are detected in advance and tracking reduces to an association problem: linking detections of the same object through frames into trajectories. Most tracking algorithms employ both motion and appearance models for data association. For multiple object tracking problems where exist many objects of the same category, a fine-grained discriminant appearance model is paramount and indispensable. Therefore, we propose an appearance-based re-identification model using deep similarity metric learning to deal with multiple object tracking in mono-camera videos. Two main contributions are reported in this dissertation: First, a deep Siamese network is employed to learn an end-to-end mapping from input images to a discriminant embedding space. Different metric learning configurations using various metrics, loss functions, deep network structures, etc., are investigated, in order to determine the best re-identification model for tracking. In addition, with an intuitive and simple classification design, the proposed model achieves satisfactory re-identification results, which are comparable to state-of-the-art approaches using triplet losses. Our approach is easy and fast to train and the learned embedding can be readily transferred onto the domain of tracking tasks. Second, we integrate our proposed re-identification model in multiple object tracking as appearance guidance for detection association. For each object to be tracked in a video, we establish an identity-related appearance model based on the learned embedding for re-identification. Similarities among detected object instances are exploited for identity classification. The collaboration and interference between appearance and motion models are also investigated. An online appearance-motion model coupling is proposed to further improve the tracking performance. Experiments on Multiple Object Tracking Challenge benchmark prove the effectiveness of our modifications, with a state-of-the-art tracking accuracy
Guillaumin, Matthieu. « Données multimodales pour l'analyse d'image ». Phd thesis, Grenoble, 2010. http://tel.archives-ouvertes.fr/tel-00522278/en/.
Texte intégralDergachyova, Olga. « Knowledge-based support for surgical workflow analysis and recognition ». Thesis, Rennes 1, 2017. http://www.theses.fr/2017REN1S059/document.
Texte intégralComputer assistance became indispensable part of modern surgical procedures. Desire of creating new generation of intelligent operating rooms incited researchers to explore problems of automatic perception and understanding of surgical situations. Situation awareness includes automatic recognition of surgical workflow. A great progress was achieved in recognition of surgical phases and gestures. Yet, there is still a blank between these two granularity levels in the hierarchy of surgical process. Very few research is focused on surgical activities carrying important semantic information vital for situation understanding. Two important factors impede the progress. First, automatic recognition and prediction of surgical activities is a highly challenging task due to short duration of activities, their great number and a very complex workflow with multitude of possible execution and sequencing ways. Secondly, very limited amount of clinical data provides not enough information for successful learning and accurate recognition. In our opinion, before recognizing surgical activities a careful analysis of elements that compose activity is necessary in order to chose right signals and sensors that will facilitate recognition. We used a deep learning approach to assess the impact of different semantic elements of activity on its recognition. Through an in-depth study we determined a minimal set of elements sufficient for an accurate recognition. Information about operated anatomical structure and surgical instrument was shown to be the most important. We also addressed the problem of data deficiency proposing methods for transfer of knowledge from other domains or surgeries. The methods of word embedding and transfer learning were proposed. They demonstrated their effectiveness on the task of next activity prediction offering 22% increase in accuracy. In addition, pertinent observations about the surgical practice were made during the study. In this work, we also addressed the problem of insufficient and improper validation of recognition methods. We proposed new validation metrics and approaches for assessing the performance that connect methods to targeted applications and better characterize capacities of the method. The work described in this these aims at clearing obstacles blocking the progress of the domain and proposes a new perspective on the problem of surgical workflow recognition