Academic literature on the topic 'Fully- and weakly-Supervised learning'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Fully- and weakly-Supervised learning.'
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.
Journal articles on the topic "Fully- and weakly-Supervised learning"
1
Cuypers, Suzanna, Maarten Bassier, and Maarten Vergauwen. "Deep Learning on Construction Sites: A Case Study of Sparse Data Learning Techniques for Rebar Segmentation." Sensors 21, no. 16 (August 11, 2021): 5428. http://dx.doi.org/10.3390/s21165428.
Full textAbstract:
With recent advancements in deep learning models for image interpretation, it has finally become possible to automate construction site monitoring processes that rely on remote sensing. However, the major drawback of these models is their dependency on large datasets of training images labeled at pixel level, which have to be produced manually by skilled personnel. To alleviate the need for training data, this study evaluates weakly- and semi-supervised semantic segmentation models for construction site imagery to efficiently automate monitoring tasks. As a case study, we compare fully-, weakly- and semi-supervised methods for the detection of rebar covers, which are useful for quality control. In the experiments, recent models, i.e., IRNet, DeepLabv3+ and the cross-consistency training model, are compared for their ability to segment rebar covers from construction site imagery with minimal manual input. The results show that weakly- and semi-supervised models can indeed approach the performance of fully-supervised models, with the majority of the target objects being properly found. Through this study, construction site stakeholders are provided with detailed information on how tp leverage deep learning for efficient construction site monitoring and weigh preprocessing, training and testing efforts against each other in order to decide between fully-, weakly- and semi-supervised training.
2
Wang, Ning, Jiajun Deng, and Mingbo Jia. "Cycle-Consistency Learning for Captioning and Grounding." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 6 (March 24, 2024): 5535–43. http://dx.doi.org/10.1609/aaai.v38i6.28363.
Full textAbstract:
We present that visual grounding and image captioning, which perform as two mutually inverse processes, can be bridged together for collaborative training by careful designs. By consolidating this idea, we introduce CyCo, a cyclic-consistent learning framework to ameliorate the independent training pipelines of visual grounding and image captioning. The proposed framework (1) allows the semi-weakly supervised training of visual grounding; (2) improves the performance of fully supervised visual grounding; (3) yields a general captioning model that can describe arbitrary image regions. Extensive experiments show that our fully supervised grounding model achieves state-of-the-art performance, and the semi-weakly supervised one also exhibits competitive performance compared to the fully supervised counterparts. Our image captioning model has the capability to freely describe image regions and meanwhile shows impressive performance on prevalent captioning benchmarks.
3
Wang, Guangyao. "A Study of Object Detection Based on Weakly Supervised Learning." International Journal of Computer Science and Information Technology 2, no. 1 (March 25, 2024): 476–78. http://dx.doi.org/10.62051/ijcsit.v2n1.50.
Full textAbstract:
Object detection is one of the important research contents in the field of computer vision. At present, the classical object detection methods can be divided into two categories: fully supervised-based target detection and weakly supervised-based target detection. Since the fully supervised object detection model requires a large number of training data with category labels and target bounding boxes, and such labeled data is difficult to obtain, it is of great significance to explore the weakly supervised object detection method that only needs category label data.
4
Adke, Shrinidhi, Changying Li, Khaled M. Rasheed, and Frederick W. Maier. "Supervised and Weakly Supervised Deep Learning for Segmentation and Counting of Cotton Bolls Using Proximal Imagery." Sensors 22, no. 10 (May 12, 2022): 3688. http://dx.doi.org/10.3390/s22103688.
Full textAbstract:
The total boll count from a plant is one of the most important phenotypic traits for cotton breeding and is also an important factor for growers to estimate the final yield. With the recent advances in deep learning, many supervised learning approaches have been implemented to perform phenotypic trait measurement from images for various crops, but few studies have been conducted to count cotton bolls from field images. Supervised learning models require a vast number of annotated images for training, which has become a bottleneck for machine learning model development. The goal of this study is to develop both fully supervised and weakly supervised deep learning models to segment and count cotton bolls from proximal imagery. A total of 290 RGB images of cotton plants from both potted (indoor and outdoor) and in-field settings were taken by consumer-grade cameras and the raw images were divided into 4350 image tiles for further model training and testing. Two supervised models (Mask R-CNN and S-Count) and two weakly supervised approaches (WS-Count and CountSeg) were compared in terms of boll count accuracy and annotation costs. The results revealed that the weakly supervised counting approaches performed well with RMSE values of 1.826 and 1.284 for WS-Count and CountSeg, respectively, whereas the fully supervised models achieve RMSE values of 1.181 and 1.175 for S-Count and Mask R-CNN, respectively, when the number of bolls in an image patch is less than 10. In terms of data annotation costs, the weakly supervised approaches were at least 10 times more cost efficient than the supervised approach for boll counting. In the future, the deep learning models developed in this study can be extended to other plant organs, such as main stalks, nodes, and primary and secondary branches. Both the supervised and weakly supervised deep learning models for boll counting with low-cost RGB images can be used by cotton breeders, physiologists, and growers alike to improve crop breeding and yield estimation.
5
Ni, Ansong, Pengcheng Yin, and Graham Neubig. "Merging Weak and Active Supervision for Semantic Parsing." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (April 3, 2020): 8536–43. http://dx.doi.org/10.1609/aaai.v34i05.6375.
Full textAbstract:
A semantic parser maps natural language commands (NLs) from the users to executable meaning representations (MRs), which are later executed in certain environment to obtain user-desired results. The fully-supervised training of such parser requires NL/MR pairs, annotated by domain experts, which makes them expensive to collect. However, weakly-supervised semantic parsers are learnt only from pairs of NL and expected execution results, leaving the MRs latent. While weak supervision is cheaper to acquire, learning from this input poses difficulties. It demands that parsers search a large space with a very weak learning signal and it is hard to avoid spurious MRs that achieve the correct answer in the wrong way. These factors lead to a performance gap between parsers trained in weakly- and fully-supervised setting. To bridge this gap, we examine the intersection between weak supervision and active learning, which allows the learner to actively select examples and query for manual annotations as extra supervision to improve the model trained under weak supervision. We study different active learning heuristics for selecting examples to query, and various forms of extra supervision for such queries. We evaluate the effectiveness of our method on two different datasets. Experiments on the WikiSQL show that by annotating only 1.8% of examples, we improve over a state-of-the-art weakly-supervised baseline by 6.4%, achieving an accuracy of 79.0%, which is only 1.3% away from the model trained with full supervision. Experiments on WikiTableQuestions with human annotators show that our method can improve the performance with only 100 active queries, especially for weakly-supervised parsers learnt from a cold start. 1
6
Colin, Aurélien, Ronan Fablet, Pierre Tandeo, Romain Husson, Charles Peureux, Nicolas Longépé, and Alexis Mouche. "Semantic Segmentation of Metoceanic Processes Using SAR Observations and Deep Learning." Remote Sensing 14, no. 4 (February 11, 2022): 851. http://dx.doi.org/10.3390/rs14040851.
Full textAbstract:
Through the Synthetic Aperture Radar (SAR) embarked on the satellites Sentinel-1A and Sentinel-1B of the Copernicus program, a large quantity of observations is routinely acquired over the oceans. A wide range of features from both oceanic (e.g., biological slicks, icebergs, etc.) and meteorologic origin (e.g., rain cells, wind streaks, etc.) are distinguishable on these acquisitions. This paper studies the semantic segmentation of ten metoceanic processes either in the context of a large quantity of image-level groundtruths (i.e., weakly-supervised framework) or of scarce pixel-level groundtruths (i.e., fully-supervised framework). Our main result is that a fully-supervised model outperforms any tested weakly-supervised algorithm. Adding more segmentation examples in the training set would further increase the precision of the predictions. Trained on 20 × 20 km imagettes acquired from the WV acquisition mode of the Sentinel-1 mission, the model is shown to generalize, under some assumptions, to wide-swath SAR data, which further extents its application domain to coastal areas.
7
Cai, Tingting, Hongping Yan, Kun Ding, Yan Zhang, and Yueyue Zhou. "WSPolyp-SAM: Weakly Supervised and Self-Guided Fine-Tuning of SAM for Colonoscopy Polyp Segmentation." Applied Sciences 14, no. 12 (June 8, 2024): 5007. http://dx.doi.org/10.3390/app14125007.
Full textAbstract:
Ensuring precise segmentation of colorectal polyps holds critical importance in the early diagnosis and treatment of colorectal cancer. Nevertheless, existing deep learning-based segmentation methods are fully supervised, requiring extensive, precise, manual pixel-level annotation data, which leads to high annotation costs. Additionally, it remains challenging to train large-scale segmentation models when confronted with limited colonoscopy data. To address these issues, we introduce the general segmentation foundation model—the Segment Anything Model (SAM)—into the field of medical image segmentation. Fine-tuning the foundation model is an effective approach to tackle sample scarcity. However, current SAM fine-tuning techniques still rely on precise annotations. To overcome this limitation, we propose WSPolyp-SAM, a novel weakly supervised approach for colonoscopy polyp segmentation. WSPolyp-SAM utilizes weak annotations to guide SAM in generating segmentation masks, which are then treated as pseudo-labels to guide the fine-tuning of SAM, thereby reducing the dependence on precise annotation data. To improve the reliability and accuracy of pseudo-labels, we have designed a series of enhancement strategies to improve the quality of pseudo-labels and mitigate the negative impact of low-quality pseudo-labels. Experimental results on five medical image datasets demonstrate that WSPolyp-SAM outperforms current fully supervised mainstream polyp segmentation networks on the Kvasir-SEG, ColonDB, CVC-300, and ETIS datasets. Furthermore, by using different amounts of training data in weakly supervised and fully supervised experiments, it is found that weakly supervised fine-tuning can save 70% to 73% of annotation time costs compared to fully supervised fine-tuning. This study provides a new perspective on the combination of weakly supervised learning and SAM models, significantly reducing annotation time and offering insights for further development in the field of colonoscopy polyp segmentation.
8
Hong, Yining, Qing Li, Daniel Ciao, Siyuan Huang, and Song-Chun Zhu. "Learning by Fixing: Solving Math Word Problems with Weak Supervision." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 6 (May 18, 2021): 4959–67. http://dx.doi.org/10.1609/aaai.v35i6.16629.
Full textAbstract:
Previous neural solvers of math word problems (MWPs) are learned with full supervision and fail to generate diverse solutions. In this paper, we address this issue by introducing a weakly-supervised paradigm for learning MWPs. Our method only requires the annotations of the final answers and can generate various solutions for a single problem. To boost weakly-supervised learning, we propose a novel learning-by-fixing (LBF) framework, which corrects the misperceptions of the neural network via symbolic reasoning. Specifically, for an incorrect solution tree generated by the neural network, the fixing mechanism propagates the error from the root node to the leaf nodes and infers the most probable fix that can be executed to get the desired answer. To generate more diverse solutions, tree regularization is applied to guide the efficient shrinkage and exploration of the solution space, and a memory buffer is designed to track and save the discovered various fixes for each problem. Experimental results on the Math23K dataset show the proposed LBF framework significantly outperforms reinforcement learning baselines in weakly-supervised learning. Furthermore, it achieves comparable top-1 and much better top-3/5 answer accuracies than fully-supervised methods, demonstrating its strength in producing diverse solutions.
9
Chen, Shaolong, and Zhiyong Zhang. "A Semi-Automatic Magnetic Resonance Imaging Annotation Algorithm Based on Semi-Weakly Supervised Learning." Sensors 24, no. 12 (June 16, 2024): 3893. http://dx.doi.org/10.3390/s24123893.
Full textAbstract:
The annotation of magnetic resonance imaging (MRI) images plays an important role in deep learning-based MRI segmentation tasks. Semi-automatic annotation algorithms are helpful for improving the efficiency and reducing the difficulty of MRI image annotation. However, the existing semi-automatic annotation algorithms based on deep learning have poor pre-annotation performance in the case of insufficient segmentation labels. In this paper, we propose a semi-automatic MRI annotation algorithm based on semi-weakly supervised learning. In order to achieve a better pre-annotation performance in the case of insufficient segmentation labels, semi-supervised and weakly supervised learning were introduced, and a semi-weakly supervised learning segmentation algorithm based on sparse labels was proposed. In addition, in order to improve the contribution rate of a single segmentation label to the performance of the pre-annotation model, an iterative annotation strategy based on active learning was designed. The experimental results on public MRI datasets show that the proposed algorithm achieved an equivalent pre-annotation performance when the number of segmentation labels was much less than that of the fully supervised learning algorithm, which proves the effectiveness of the proposed algorithm.
10
Zhang, Yachao, Zonghao Li, Yuan Xie, Yanyun Qu, Cuihua Li, and Tao Mei. "Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 4 (May 18, 2021): 3421–29. http://dx.doi.org/10.1609/aaai.v35i4.16455.
Full textAbstract:
Existing methods for large-scale point cloud semantic segmentation require expensive, tedious and error-prone manual point-wise annotation. Intuitively, weakly supervised training is a direct solution to reduce the labeling costs. However, for weakly supervised large-scale point cloud semantic segmentation, too few annotations will inevitably lead to ineffective learning of network. We propose an effective weakly supervised method containing two components to solve the above problem. Firstly, we construct a pretext task, \textit{i.e.,} point cloud colorization, with a self-supervised training manner to transfer the learned prior knowledge from a large amount of unlabeled point cloud to a weakly supervised network. In this way, the representation capability of the weakly supervised network can be improved by knowledge from a heterogeneous task. Besides, to generative pseudo label for unlabeled data, a sparse label propagation mechanism is proposed with the help of generated class prototypes, which is used to measure the classification confidence of unlabeled point. Our method is evaluated on large-scale point cloud datasets with different scenarios including indoor and outdoor. The experimental results show the large gain against existing weakly supervised methods and comparable results to fully supervised methods.
Dissertations / Theses on the topic "Fully- and weakly-Supervised learning"
1
Ma, Qixiang. "Deep learning based segmentation and detection of aorta structures in CT images involving fully and weakly supervised learning." Electronic Thesis or Diss., Université de Rennes (2023-....), 2024. http://www.theses.fr/2024URENS029.
Full textAbstract:
La réparation endovasculaire des anévrismes aortiques abdominaux (EVAR) et l’implantation valvulaire aortique transcathéter (TAVI) sont des interventions endovasculaires pour lesquelles l’analyse des images CT préopératoires est une étape préalable au planning et au guidage de navigation. Dans le cas de la procédure EVAR, les travaux se concentrent spécifiquement sur la question difficile de la segmentation de l’aorte dans l’imagerie CT acquise sans produit de contraste (NCCT), non encore résolue. Dans le cas de la procédure TAVI, ils abordent la détection des repères anatomiques permettant de prédire le risque de complications et de choisir la bioprothèse. Pour relever ces défis, nous proposons des méthodes automatiques basées sur l’apprentissage profond (DL). Un modèle entièrement supervisé basé sur la fusion de caractéristiques 2D-3D est d’abord proposé pour la segmentation vasculaire dans les NCCT. Un cadre faiblement supervisé basé sur des pseudo-labels gaussiens est ensuite envisagé pour réduire et faciliter l’annotation manuelle dans la phase d’apprentissage. Des méthodes hybrides faiblement et entièrement supervisées sont finalement proposées pour étendre la segmentation à des structures vasculaires plus complexes, au-delà de l’aorte abdominale. Pour la valve aortique dans les CT cardiaques, une méthode DL de détection en deux étapes des points de repère d’intérêt et entièrement supervisée est proposée. Les résultats obtenus contribuent à l’augmentation de l’image préopératoire et du modèle numérique du patient pour les interventions endovasculaires assistées par ordinateurEndovascular aneurysm repair (EVAR) and transcatheter aortic valve implantation (TAVI) are endovascular interventions where preoperative CT image analysis is a prerequisite for planning and navigation guidance. In the case of EVAR procedures, the focus is specifically on the challenging issue of aortic segmentation in non-contrast-enhanced CT (NCCT) imaging, which remains unresolved. For TAVI procedures, attention is directed toward detecting anatomical landmarks to predict the risk of complications and select the bioprosthesis. To address these challenges, we propose automatic methods based on deep learning (DL). Firstly, a fully-supervised model based on 2D-3D features fusion is proposed for vascular segmentation in NCCTs. Subsequently, a weakly-supervised framework based on Gaussian pseudo labels is considered to reduce and facilitate manual annotation during the training phase. Finally, hybrid weakly- and fully-supervised methods are proposed to extend segmentation to more complex vascular structures beyond the abdominal aorta. When it comes to aortic valve in cardiac CT scans, a two-stage fully-supervised DL method is proposed for landmarks detection. The results contribute to enhancing preoperative imaging and the patient's digital model for computer-assisted endovascular interventions
2
Hlynur, Davíð Hlynsson. "Predicting expert moves in the game of Othello using fully convolutional neural networks." Thesis, KTH, Robotik, perception och lärande, RPL, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-210914.
Full textAbstract:
Careful feature engineering is an important factor of artificial intelligence for games. In this thesis I investigate the benefit of delegating the engineering efforts to the model rather than the features, using the board game Othello as a case study. Convolutional neural networks of varying depths are trained to play in a human-like manner by learning to predict actions from tournaments. My main result is that using a raw board state representation, a network can be trained to achieve 57.4% prediction accuracy on a test set, surpassing previous state-of-the-art in this task. The accuracy is increased to 58.3% by adding several common handcrafted features as input to the network but at the cost of more than half again as much the computation time.Noggrann funktionsteknik är en viktig faktor för artificiell intelligens för spel. I dennaavhandling undersöker jag fördelarna med att delegera teknikarbetet till modellen i ställetför de funktioner, som använder brädspelet Othello som en fallstudie. Konvolutionellaneurala nätverk av varierande djup är utbildade att spela på ett mänskligt sätt genom attlära sig att förutsäga handlingar från turneringar. Mitt främsta resultat är att ett nätverkkan utbildas för att uppnå 57,4% prediktionsnoggrannhet på en testuppsättning, vilketöverträffar tidigare toppmoderna i den här uppgiften. Noggrannheten ökar till 58.3% genomatt lägga till flera vanliga handgjorda funktioner som inmatning till nätverket, tillkostnaden för mer än hälften så mycket beräknatid.
3
Durand, Thibaut. "Weakly supervised learning for visual recognition." Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066142/document.
Full textAbstract:
Cette thèse s'intéresse au problème de la classification d'images, où l'objectif est de prédire si une catégorie sémantique est présente dans l'image, à partir de son contenu visuel. Pour analyser des images de scènes complexes, il est important d'apprendre des représentations localisées. Pour limiter le coût d'annotation pendant l'apprentissage, nous nous sommes intéressé aux modèles d'apprentissage faiblement supervisé. Dans cette thèse, nous proposons des modèles qui simultanément classifient et localisent les objets, en utilisant uniquement des labels globaux pendant l'apprentissage. L'apprentissage faiblement supervisé permet de réduire le cout d'annotation, mais en contrepartie l'apprentissage est plus difficile. Le problème principal est comment agréger les informations locales (e.g. régions) en une information globale (e.g. image). La contribution principale de cette thèse est la conception de nouvelles fonctions de pooling (agrégation) pour l'apprentissage faiblement supervisé. En particulier, nous proposons une fonction de pooling « max+min », qui unifie de nombreuses fonctions de pooling. Nous décrivons comment utiliser ce pooling dans le framework Latent Structured SVM ainsi que dans des réseaux de neurones convolutifs. Pour résoudre les problèmes d'optimisation, nous présentons plusieurs solveurs, dont certains qui permettent d'optimiser une métrique d'ordonnancement (ranking) comme l'Average Precision. Expérimentalement, nous montrons l'intérêt nos modèles par rapport aux méthodes de l'état de l'art, sur dix bases de données standard de classification d'images, incluant ImageNetThis thesis studies the problem of classification of images, where the goal is to predict if a semantic category is present in the image, based on its visual content. To analyze complex scenes, it is important to learn localized representations. To limit the cost of annotation during training, we have focused on weakly supervised learning approaches. In this thesis, we propose several models that simultaneously classify and localize objects, using only global labels during training. The weak supervision significantly reduces the cost of full annotation, but it makes learning more challenging. The key issue is how to aggregate local scores - e.g. regions - into global score - e.g. image. The main contribution of this thesis is the design of new pooling functions for weakly supervised learning. In particular, we propose a “max + min” pooling function, which unifies many pooling functions. We describe how to use this pooling in the Latent Structured SVM framework as well as in convolutional networks. To solve the optimization problems, we present several solvers, some of which allow to optimize a ranking metric such as Average Precision. We experimentally show the interest of our models with respect to state-of-the-art methods, on ten standard image classification datasets, including the large-scale dataset ImageNet
4
Durand, Thibaut. "Weakly supervised learning for visual recognition." Electronic Thesis or Diss., Paris 6, 2017. http://www.theses.fr/2017PA066142.
Full textAbstract:
Cette thèse s'intéresse au problème de la classification d'images, où l'objectif est de prédire si une catégorie sémantique est présente dans l'image, à partir de son contenu visuel. Pour analyser des images de scènes complexes, il est important d'apprendre des représentations localisées. Pour limiter le coût d'annotation pendant l'apprentissage, nous nous sommes intéressé aux modèles d'apprentissage faiblement supervisé. Dans cette thèse, nous proposons des modèles qui simultanément classifient et localisent les objets, en utilisant uniquement des labels globaux pendant l'apprentissage. L'apprentissage faiblement supervisé permet de réduire le cout d'annotation, mais en contrepartie l'apprentissage est plus difficile. Le problème principal est comment agréger les informations locales (e.g. régions) en une information globale (e.g. image). La contribution principale de cette thèse est la conception de nouvelles fonctions de pooling (agrégation) pour l'apprentissage faiblement supervisé. En particulier, nous proposons une fonction de pooling « max+min », qui unifie de nombreuses fonctions de pooling. Nous décrivons comment utiliser ce pooling dans le framework Latent Structured SVM ainsi que dans des réseaux de neurones convolutifs. Pour résoudre les problèmes d'optimisation, nous présentons plusieurs solveurs, dont certains qui permettent d'optimiser une métrique d'ordonnancement (ranking) comme l'Average Precision. Expérimentalement, nous montrons l'intérêt nos modèles par rapport aux méthodes de l'état de l'art, sur dix bases de données standard de classification d'images, incluant ImageNetThis thesis studies the problem of classification of images, where the goal is to predict if a semantic category is present in the image, based on its visual content. To analyze complex scenes, it is important to learn localized representations. To limit the cost of annotation during training, we have focused on weakly supervised learning approaches. In this thesis, we propose several models that simultaneously classify and localize objects, using only global labels during training. The weak supervision significantly reduces the cost of full annotation, but it makes learning more challenging. The key issue is how to aggregate local scores - e.g. regions - into global score - e.g. image. The main contribution of this thesis is the design of new pooling functions for weakly supervised learning. In particular, we propose a “max + min” pooling function, which unifies many pooling functions. We describe how to use this pooling in the Latent Structured SVM framework as well as in convolutional networks. To solve the optimization problems, we present several solvers, some of which allow to optimize a ranking metric such as Average Precision. We experimentally show the interest of our models with respect to state-of-the-art methods, on ten standard image classification datasets, including the large-scale dataset ImageNet
5
Raisi, Elaheh. "Weakly Supervised Machine Learning for Cyberbullying Detection." Diss., Virginia Tech, 2019. http://hdl.handle.net/10919/89100.
Full textAbstract:
The advent of social media has revolutionized human communication, significantly improving individuals' lives. It makes people closer to each other, provides access to enormous real-time information, and eases marketing and business. Despite its uncountable benefits, however, we must consider some of its negative implications such as online harassment and cyberbullying. Cyberbullying is becoming a serious, large-scale problem damaging people's online lives. This phenomenon is creating a need for automated, data-driven techniques for analyzing and detecting such behaviors. In this research, we aim to address the computational challenges associated with harassment-based cyberbullying detection in social media by developing machine-learning framework that only requires weak supervision. We propose a general framework that trains an ensemble of two learners in which each learner looks at the problem from a different perspective. One learner identifies bullying incidents by examining the language content in the message; another learner considers the social structure to discover bullying.
Each learner is using different body of information, and the individual learner co-train one another to come to an agreement about the bullying concept. The models estimate whether each social interaction is bullying by optimizing an objective function that maximizes the consistency between these detectors.
We first developed a model we referred to as participant-vocabulary consistency, which is an ensemble of two linear language-based and user-based models. The model is trained by providing a set of seed key-phrases that are indicative of bullying language. The results were promising, demonstrating its effectiveness and usefulness in recovering known bullying words, recognizing new bullying words, and discovering users involved in cyberbullying. We have extended this co-trained ensemble approach with two complementary goals: (1) using nonlinear embeddings as model families, (2) building a fair language-based detector. For the first goal, we incorporated the efficacy of distributed representations of words and nodes such as deep, nonlinear models. We represent words and users as low-dimensional vectors of real numbers as the input to language-based and user-based classifiers, respectively. The models are trained by optimizing an objective function that balances a co-training loss with a weak-supervision loss. Our experiments on Twitter, Ask.fm, and Instagram data show that deep ensembles outperform non-deep methods for weakly supervised harassment detection. For the second goal, we geared this research toward a very important topic in any online automated harassment detection: fairness against particular targeted groups including race, gender, religion, and sexual orientations. Our goal is to decrease the sensitivity of models to language describing particular social groups. We encourage the learning algorithm to avoid discrimination in the predictions by adding an unfairness penalty term to the objective function. We quantitatively and qualitatively evaluate the effectiveness of our proposed general framework on synthetic data and data from Twitter using post-hoc, crowdsourced annotation. In summary, this dissertation introduces a weakly supervised machine learning framework for harassment-based cyberbullying detection using both messages and user roles in social media.Doctor of Philosophy
Social media has become an inevitable part of individuals social and business lives. Its benefits, however, come with various negative consequences such as online harassment, cyberbullying, hate speech, and online trolling especially among the younger population. According to the American Academy of Child and Adolescent Psychiatry,1 victims of bullying can suffer interference to social and emotional development and even be drawn to extreme behavior such as attempted suicide. Any widespread bullying enabled by technology represents a serious social health threat. In this research, we develop automated, data-driven methods for harassment-based cyberbullying detection. The availability of tools such as these can enable technologies that reduce the harm and toxicity created by these detrimental behaviors. Our general framework is based on consistency of two detectors that co-train one another. One learner identifies bullying incidents by examining the language content in the message; another learner considers social structure to discover bullying. When designing the general framework, we address three tasks: First, we use machine learning with weak supervision, which significantly alleviates the need for human experts to perform tedious data annotation. Second, we incorporate the efficacy of distributed representations of words and nodes such as deep, nonlinear models in the framework to improve the predictive power of models. Finally, we decrease the sensitivity of the framework to language describing particular social groups including race, gender, religion, and sexual orientation. This research represents important steps toward improving technological capability for automatic cyberbullying detection.
6
Hanwell, David. "Weakly supervised learning of visual semantic attributes." Thesis, University of Bristol, 2014. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.687063.
Full textAbstract:
There are at present many billions of images on the internet, only a fraction of which are labelled according to their semantic content. To automatically provide labels for the rest, models of visual semantic concepts must be created. Such models are traditionally trained using images which have been manually acquired, segmented, and labelled. In this thesis, we submit that such models can be learned automatically using those few images which have already been labelled, either directly by their creators, or indirectly by their associated text. Such imagery can be acquired easily, cheaply, and in large quantities, using web image searches. Though there has been some work towards learning from such weakly labelled data, all methods yet proposed require more than a minimum of human effort. In this thesis we put forth a number of methods for reliably learning models of visual semantic attributes using only the raw, unadulterated results of web image searches. The proposed methods do not require any human input beyond specifying the names of the attributes to be learned. We also present means of identifying and localising learned attributes in challenging, real-world images. Our methods are of a probabilistic nature, and make extensive use of multivariate Gaussian mixture models to represent both data and learned models. The contributions of this thesis also include several tools for acquiring and comparing these distributions, including a novel clustering algorithm. We apply our weakly supervised learning methods to the training of models of a variety of visual semantic attributes including colour and pattern terms. Detection and localization of the learned attributes in unseen realworld images is demonstrated, and both quantitative and qualitative results are presented. We compare against other work, including both general methods of weakly supervised learning, and more attribute specific methods. We apply our learning methods to the training sets of previous works, and assess their performance on the test sets used by other authors. Our results show that our methods give better results than the current state of the art.
7
Kumar, M. Pawan. "Weakly Supervised Learning for Structured Output Prediction." Habilitation à diriger des recherches, École normale supérieure de Cachan - ENS Cachan, 2013. http://tel.archives-ouvertes.fr/tel-00943602.
Full textAbstract:
We consider the problem of learning the parameters of a structured output prediction model, that is, learning to predict elements of a complex interdependent output space that correspond to a given input. Unlike many of the existing approaches, we focus on the weakly supervised setting, where most (or all) of the training samples have only been partially annotated. Given such a weakly supervised dataset, our goal is to estimate accurate parameters of the model by minimizing the regularized empirical risk, where the risk is measured by a user-specified loss function. This task has previously been addressed by the well-known latent support vector machine (latent SVM) framework. We argue that, while latent SVM offers a computational efficient solution to loss-based weakly supervised learning, it suffers from the following three drawbacks: (i) the optimization problem corresponding to latent SVM is a difference-of-convex program, which is non-convex, and hence susceptible to bad local minimum solutions; (ii) the prediction rule of latent SVM only relies on the most likely value of the latent variables, and not the uncertainty in the latent variable values; and (iii) the loss function used to measure the risk is restricted to be independent of true (unknown) value of the latent variables. We address the the aforementioned drawbacks using three novel contributions. First, inspired by human learning, we design an automatic self-paced learning algorithm for latent SVM, which builds on the intuition that the learner should be presented in the training samples in a meaningful order that facilitates learning: starting frome easy samples and gradually moving to harder samples. Our algorithm simultaneously selects the easy samples and updates the parameters at each iteration by solving a biconvex optimization problem. Second, we propose a new family of LVMs called max-margin min-entropy (M3E) models, which includes latent SVM as a special case. Given an input, an M3E model predicts the output with the smallest corresponding Renyi entropy of generalized distribution, which relies not only on the probability of the output but also the uncertainty of the latent variable values. Third, we propose a novel learning framework for learning with general loss functions that may depend on the latent variables. Specifically, our framework simultaneously estimates two distributions: (i) a conditional distribution to model the uncertainty of the latent variables for a given input-output pair; and (ii) a delta distribution to predict the output and the latent variables for a given input. During learning, we encourage agreement between the two distributions by minimizing a loss-based dissimilarity coefficient. We demonstrate the efficacy of our contributions on standard machine learning applications using publicly available datasets.
8
Nodet, Pierre. "Biquality learning : from weakly supervised learning to distribution shifts." Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPASG030.
Full textAbstract:
Le domaine de l'apprentissage avec des faiblesses en supervision est appelé apprentissage faiblement supervisé et regroupe une variété de situations où la vérité terrain collectée est imparfaite. Les étiquettes collectées peuvent souffrir de mauvaise qualité, de non-adaptabilité ou de quantité insuffisante. Dans ce mémoire nous proposons une nouvelle taxonomie de l'apprentissage faiblement supervisé sous la forme d'un cube continu appelé le cube de la supervision faible qui englobe toutes les faiblesses en supervision. Pour concevoir des algorithmes capables de gérer toutes supervisions faibles, nous supposons la disponibilité d'un petit ensemble de données de confiance, sans biais ni corruption, en plus de l'ensemble de données potentiellement corrompu. L'ensemble de données de confiance permet de définir un cadre de travail formel appelé apprentissage biqualité. Nous avons examiné l'état de l'art de ces algorithmes qui supposent la disponibilité d'un petit jeu de données de confiance. Dans ce cadre, nous proposons un algorithme basé sur la repondération préférentielle pour l'apprentissage biqualité (IRBL). Cette approche agnostique du classificateur est basée sur l'estimation empirique de la dérivée de Radon-Nikodym (RND), pour apprendre un estimateur conforme au risque sur des données non fiables repesées. Nous étendrons ensuite le cadre proposé aux décalages de jeu de données. Les décalages de jeu de données se produisent lorsque la distribution des données observée au moment de l'apprentissage est différente de celle attendue au moment de la prédiction. Nous proposons alors une version améliorée d'IRBL, appelée IRBL2, capable de gérer de tels décalages de jeux de données. Nous proposons aussi KPDR basé sur le même fondement théorique mais axé sur le décalage de covariable plutôt que le bruit des étiquettes. Pour diffuser et démocratiser le cadre de l'apprentissage biqualité, nous rendons ouvert le code source d'une bibliothèque Python à la Scikit-Learn pour l'apprentissage biqualité : biquality-learnThe field of Learning with weak supervision is called Weakly Supervised Learning and aggregates a variety of situations where the collected ground truth is imperfect. The collected labels may suffer from bad quality, non-adaptability, or insufficient quantity. In this report, we propose a novel taxonomy of Weakly Supervised Learning as a continuous cube called the Weak Supervision Cube that encompasses all of the weaknesses of supervision. To design algorithms capable of handling any weak supervisions, we suppose the availability of a small trusted dataset, without bias and corruption, in addition to the potentially corrupted dataset. The trusted dataset allows the definition of a generic learning framework named Biquality Learning. We review the state-of-the-art of these algorithms that assumed the availability of a small trusted dataset. Under this framework, we propose an algorithm based on Importance Reweighting for Biquality Learning (IRBL). This classifier-agnostic approach is based on the empirical estimation of the Radon-Nikodym derivative (RND), to build a risk-consistent estimator on reweighted untrusted data. Then we extend the proposed framework to dataset shifts. Dataset shifts happen when the data distribution observed at training time is different from what is expected from the data distribution at testing time. So we propose an improved version of IRBL named IRBL2, capable of handling such dataset shifts. Additionally, we propose another algorithm named KPDR based on the same theory but focused on covariate shift instead of the label noise formulation. To diffuse and democratize the Biquality Learning Framework, we release an open-source Python library à la Scikit-Learn for Biquality Learning named biquality-learn
9
Ruiz, Ovejero Adrià. "Weakly-supervised learning for automatic facial behaviour analysis." Doctoral thesis, Universitat Pompeu Fabra, 2017. http://hdl.handle.net/10803/457708.
Full textAbstract:
In this Thesis we focus on Automatic Facial Behavior Analysis, which attempts to develop autonomous systems able to recognize and understand human facial expressions. Given the amount of information expressed by facial gestures, this type of systems has potential applications in multiple domains such as Human Computer Interaction, Marketing or Healthcare. For this reason, the topic has attracted a lot of attention in Computer Vision and Machine Learning communities during the past two decades. Despite the advances in the field, most of facial expression analysis problems can be considered far from being solved.
In this context, this dissertation is motivated by the observation that the vast majority of methods in the literature has followed the Supervised Learning paradigm, where models are trained by using data explicitly labelled according to the target problem. However, this approach presents some limitations given the difficult annotation process typically involved in facial expression analysis tasks. In order to address this challenge, we propose to pose Automatic Facial Behavior Analysis from a weakly-supervised perspective. Different from the fully-supervised strategy, weakly-supervised models are trained by using labels which are easy to collect but only provide partial information about the task that aims to be solved (i.e, weak-labels). Following this idea, we present different weakly-supervised methods to address standard problems in the field such as Action Unit Recognition, Expression Intensity Estimation or Affect Analysis. Our results obtained by evaluating the proposed approaches on these tasks, demonstrate that weakly-supervised learning may provide a potential solution to alleviate the need of annotated data in Automatic Facial Behavior Analysis. Moreover we also show how these approaches are able to facilitate the labelling process of databases designed for this purpose.Aquesta tesi doctoral se centra en el problema de l'Anàlisi Automàtic del Comportament Facial, on l'objectiu és desenvolupar sistemes autònoms capaços de reconèixer i entendre les expressions facials humanes. Donada la quantitat d'informació que es pot extreure d'aquestes expressions, sistemes d'aquest tipus tenen multitud d'aplicacions en camps com la Interacció Home-Màquina, el Marketing o l'Assistència Clínica. Per aquesta raó, investigadors en Visió per Computador i Aprenentatge Automàtic han destinat molts esforços en les últimes dècades per tal d'aconseguir avenços en aquest sentit. Malgrat això, la majoria de problemes relacionats amb l'anàlisi automàtic d'expressions facials encara estan lluny de ser conisderats com a resolts. En aquest context, aquesta tesi està motivada pel fet que la majoria de mètodes proposats fins ara han seguit el paradigma d'aprenentatge supervisat, on els models són entrenats mitjançant dades anotades explícitament en funció del problema a resoldre. Desafortunadament, aquesta estratègia té grans limitacions donat que l'anotació d'expressions en bases de dades és una tasca molt costosa i lenta. Per tal d'afrontar aquest repte, aquesta tesi proposa encarar l'Anàlisi Automàtic del Comportament Facial mitjançant el paradigma d'aprenentatge dèbilment supervisat. A diferència del cas anterior, aquests models poden ser entrenats utilitzant etiquetes que són fàcils d'anotar però que només donen informació parcial sobre la tasca que es vol aprendre. Seguint aquesta idea, desenvolupem un conjunt de mètodes per tal de resoldre problemes típics en el camp com el reconeixement d' "Action Units", l'Estimació d'Intensitat d'Expressions Facials o l'Anàlisi Emocional. Els resultats obtinguts avaluant els mètodes presentats en aquestes tasques, demostren que l'aprenentatge dèbilment supervisat pot ser una solució per tal de reduir l'esforç d'anotació en l'Anàlisi Automàtic del Comportament Facial. De la mateixa manera, aquests mètodes es mostren útils a l'hora de facilitar el procés d'etiquetatge de bases de dades creades per aquest propòsit.
10
Siva, Parthipan. "Automatic annotation for weakly supervised learning of detectors." Thesis, Queen Mary, University of London, 2012. http://qmro.qmul.ac.uk/xmlui/handle/123456789/3359.
Full textAbstract:
Object detection in images and action detection in videos are among the most widely studied computer vision problems, with applications in consumer photography, surveillance, and automatic media tagging. Typically, these standard detectors are fully supervised, that is they require a large body of training data where the locations of the objects/actions in images/videos have been manually annotated. With the emergence of digital media, and the rise of high-speed internet, raw images and video are available for little to no cost. However, the manual annotation of object and action locations remains tedious, slow, and expensive. As a result there has been a great interest in training detectors with weak supervision where only the presence or absence of object/action in image/video is needed, not the location. This thesis presents approaches for weakly supervised learning of object/action detectors with a focus on automatically annotating object and action locations in images/videos using only binary weak labels indicating the presence or absence of object/action in images/videos. First, a framework for weakly supervised learning of object detectors in images is presented. In the proposed approach, a variation of multiple instance learning (MIL) technique for automatically annotating object locations in weakly labelled data is presented which, unlike existing approaches, uses inter-class and intra-class cue fusion to obtain the initial annotation. The initial annotation is then used to start an iterative process in which standard object detectors are used to refine the location annotation. Finally, to ensure that the iterative training of detectors do not drift from the object of interest, a scheme for detecting model drift is also presented. Furthermore, unlike most other methods, our weakly supervised approach is evaluated on data without manual pose (object orientation) annotation. Second, an analysis of the initial annotation of objects, using inter-class and intra-class cues, is carried out. From the analysis, a new method based on negative mining (NegMine) is presented for the initial annotation of both object and action data. The NegMine based approach is a much simpler formulation using only inter-class measure and requires no complex combinatorial optimisation but can still meet or outperform existing approaches including the previously pre3 sented inter-intra class cue fusion approach. Furthermore, NegMine can be fused with existing approaches to boost their performance. Finally, the thesis will take a step back and look at the use of generic object detectors as prior knowledge in weakly supervised learning of object detectors. These generic object detectors are typically based on sampling saliency maps that indicate if a pixel belongs to the background or foreground. A new approach to generating saliency maps is presented that, unlike existing approaches, looks beyond the current image of interest and into images similar to the current image. We show that our generic object proposal method can be used by itself to annotate the weakly labelled object data with surprisingly high accuracy.
Books on the topic "Fully- and weakly-Supervised learning"
1
Munro, Paul. Self-supervised learning of concepts by single units and "weakly local" representations. Pittsburgh, PA: School of Library and Information Science, University of Pittsburgh, 1988.
Find full text
2
Robert, Tibshirani, and Friedman J. H, eds. The elements of statistical learning: Data mining, inference, and prediction : with 200 full-color illustrations. New York: Springer, 2001.
Find full text
3
Munro, Paul. Self-supervised learning of concepts by single units and "weakly local" representations. School of Library and Information Science, University of Pittsburgh, 1988.
Find full text
4
Unsupervised and Weakly-Supervised Learning of Localized Texture Patterns of Lung Diseases on Computed Tomography. [New York, N.Y.?]: [publisher not identified], 2019.
Find full textBook chapters on the topic "Fully- and weakly-Supervised learning"
1
Suresh, Sundaram, Narasimhan Sundararajan, and Ramasamy Savitha. "Fully Complex-valued Relaxation Networks." In Supervised Learning with Complex-valued Neural Networks, 73–83. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013. http://dx.doi.org/10.1007/978-3-642-29491-4_4.
Full text
2
Tran, Manuel, Sophia J. Wagner, Melanie Boxberg, and Tingying Peng. "S5CL: Unifying Fully-Supervised, Self-supervised, and Semi-supervised Learning Through Hierarchical Contrastive Learning." In Lecture Notes in Computer Science, 99–108. Cham: Springer Nature Switzerland, 2022. http://dx.doi.org/10.1007/978-3-031-16434-7_10.
Full text
3
Suresh, Sundaram, Narasimhan Sundararajan, and Ramasamy Savitha. "Fully Complex-valued Multi Layer Perceptron Networks." In Supervised Learning with Complex-valued Neural Networks, 31–47. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013. http://dx.doi.org/10.1007/978-3-642-29491-4_2.
Full text
4
Trivedi, Devharsh, Aymen Boudguiga, and Nikos Triandopoulos. "SigML: Supervised Log Anomaly with Fully Homomorphic Encryption." In Cyber Security, Cryptology, and Machine Learning, 372–88. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-34671-2_26.
Full text
5
Baur, Christoph, Shadi Albarqouni, and Nassir Navab. "Semi-supervised Deep Learning for Fully Convolutional Networks." In Medical Image Computing and Computer Assisted Intervention − MICCAI 2017, 311–19. Cham: Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-66179-7_36.
Full text
6
Suresh, Sundaram, Narasimhan Sundararajan, and Ramasamy Savitha. "A Fully Complex-valued Radial Basis Function Network and Its Learning Algorithm." In Supervised Learning with Complex-valued Neural Networks, 49–71. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013. http://dx.doi.org/10.1007/978-3-642-29491-4_3.
Full text
7
Moukafih, Youness, Abdelghani Ghanem, Karima Abidi, Nada Sbihi, Mounir Ghogho, and Kamel Smaili. "SimSCL: A Simple Fully-Supervised Contrastive Learning Framework for Text Representation." In Lecture Notes in Computer Science, 728–38. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-97546-3_59.
Full text
8
Saha, Pramit, Divyanshu Mishra, and J. Alison Noble. "Rethinking Semi-Supervised Federated Learning: How to Co-train Fully-Labeled and Fully-Unlabeled Client Imaging Data." In Lecture Notes in Computer Science, 414–24. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-43895-0_39.
Full text
9
Torresani, Lorenzo. "Weakly Supervised Learning." In Computer Vision, 883–85. Boston, MA: Springer US, 2014. http://dx.doi.org/10.1007/978-0-387-31439-6_308.
Full text
10
Mehmood, Usama, Shouvik Roy, Radu Grosu, Scott A. Smolka, Scott D. Stoller, and Ashish Tiwari. "Neural Flocking: MPC-Based Supervised Learning of Flocking Controllers." In Lecture Notes in Computer Science, 1–16. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-45231-5_1.
Full textAbstract:
AbstractWe show how a symmetric and fully distributed flocking controller can be synthesized using Deep Learning from a centralized flocking controller. Our approach is based on Supervised Learning, with the centralized controller providing the training data, in the form of trajectories of state-action pairs. We use Model Predictive Control (MPC) for the centralized controller, an approach that we have successfully demonstrated on flocking problems. MPC-based flocking controllers are high-performing but also computationally expensive. By learning a symmetric and distributed neural flocking controller from a centralized MPC-based one, we achieve the best of both worlds: the neural controllers have high performance (on par with the MPC controllers) and high efficiency. Our experimental results demonstrate the sophisticated nature of the distributed controllers we learn. In particular, the neural controllers are capable of achieving myriad flocking-oriented control objectives, including flocking formation, collision avoidance, obstacle avoidance, predator avoidance, and target seeking. Moreover, they generalize the behavior seen in the training data to achieve these objectives in a significantly broader range of scenarios. In terms of verification of our neural flocking controller, we use a form of statistical model checking to compute confidence intervals for its convergence rate and time to convergence.
Conference papers on the topic "Fully- and weakly-Supervised learning"
1
Gliga, Lavinius-Ioan, Jeroen Zegers, Carlos Tiana Gomez, and Pieter Bovijn. "Self, Semi and Fully Supervised Learning for Autoencoders using Ternary Classification." In 2024 IEEE International Conference on Prognostics and Health Management (ICPHM), 33–40. IEEE, 2024. http://dx.doi.org/10.1109/icphm61352.2024.10627326.
Full text
2
Tang, Yi, Yi Gao, Yong-gang Luo, Ju-Cheng Yang, Miao Xu, and Min-Ling Zhang. "Unlearning from Weakly Supervised Learning." In Thirty-Third International Joint Conference on Artificial Intelligence {IJCAI-24}. California: International Joint Conferences on Artificial Intelligence Organization, 2024. http://dx.doi.org/10.24963/ijcai.2024/553.
Full textAbstract:
Machine unlearning provides users with the right to remove their privacy data from a well-trained model. Existing approaches of machine unlearning mainly focus on exploring data removing within supervised learning (SL) tasks. However, weakly supervised learning (WSL) is more applicable to real-world scenarios since collecting WSL data is less laborious than collecting fully supervised data. In this paper, we first propose a machine unlearning approach for WSL by updating the model parameters. Motivated by the uniform distributions of untrained model predictions, we derive a formulated target to force the model's predictions of removed data to be indistinguishable. This encourages the model to forget its ability to recognize features of data slated for unlearning. Moreover, we employ formulated targets to transform the classification unlearning into the convex regression, which can significantly reduce computational cost and avoid extra information storage during the training process. Additionally, we discuss how to design a target to ensure the models' predictions of removed data being indistinguishable in different learning scenarios, e.g., SL or WSL. As the flexibility in formulating targets, the proposed approach effectively deals with the WSL problem while still excels in SL models. Empirical studies show the superiority of the proposed approach.
3
Soltanian-Zadeh, Somayyeh, Kazuhiro Kurokawa, Zhuolin Liu, Daniel X. Hammer, Donald T. Miller, and Sina Farsiu. "Fully automatic quantification of individual ganglion cells from AO-OCT volumes via weakly supervised learning." In Ophthalmic Technologies XXX, edited by Fabrice Manns, Per G. Söderberg, and Arthur Ho. SPIE, 2020. http://dx.doi.org/10.1117/12.2543964.
Full text
4
Liu, Lu, Tianyi Zhou, Guodong Long, Jing Jiang, Lina Yao, and Chengqi Zhang. "Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/418.
Full textAbstract:
A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapted to new tasks. However, they do not fully explore weakly-supervised information, which is usually free or cheap to collect. In this paper, we show that weakly-labeled data can significantly improve the performance of meta-learning on few-shot classification. We propose prototype propagation network (PPN) trained on few-shot tasks together with data annotated by coarse-label. Given a category graph of the targeted fine-classes and some weakly-labeled coarse-classes, PPN learns an attention mechanism which propagates the prototype of one class to another on the graph, so that the K-nearest neighbor (KNN) classifier defined on the propagated prototypes results in high accuracy across different few-shot tasks. The training tasks are generated by subgraph sampling, and the training objective is obtained by accumulating the level-wise classification loss on the subgraph. On two benchmarks, PPN significantly outperforms most recent few-shot learning methods in different settings, even when they are also allowed to train on weakly-labeled data.
5
Wang, Jiapeng, Tianwei Wang, Guozhi Tang, Lianwen Jin, Weihong Ma, Kai Ding, and Yichao Huang. "Tag, Copy or Predict: A Unified Weakly-Supervised Learning Framework for Visual Information Extraction using Sequences." In Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}. California: International Joint Conferences on Artificial Intelligence Organization, 2021. http://dx.doi.org/10.24963/ijcai.2021/150.
Full textAbstract:
Visual information extraction (VIE) has attracted increasing attention in recent years. The existing methods usually first organized optical character recognition (OCR) results in plain texts and then utilized token-level category annotations as supervision to train a sequence tagging model. However, it expends great annotation costs and may be exposed to label confusion, the OCR errors will also significantly affect the final performance. In this paper, we propose a unified weakly-supervised learning framework called TCPNet (Tag, Copy or Predict Network), which introduces 1) an efficient encoder to simultaneously model the semantic and layout information in 2D OCR results, 2) a weakly-supervised training method that utilizes only sequence-level supervision; and 3) a flexible and switchable decoder which contains two inference modes: one (Copy or Predict Mode) is to output key information sequences of different categories by copying a token from the input or predicting one in each time step, and the other (Tag Mode) is to directly tag the input sequence in a single forward pass. Our method shows new state-of-the-art performance on several public benchmarks, which fully proves its effectiveness.
6
Wu, Yuanchen, Xiaoqiang Li, Songmin Dai, Jide Li, Tong Liu, and Shaorong Xie. "Hierarchical Semantic Contrast for Weakly Supervised Semantic Segmentation." In Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}. California: International Joint Conferences on Artificial Intelligence Organization, 2023. http://dx.doi.org/10.24963/ijcai.2023/171.
Full textAbstract:
Weakly supervised semantic segmentation (WSSS) with image-level annotations has achieved great processes through class activation map (CAM). Since vanilla CAMs are hardly served as guidance to bridge the gap between full and weak supervision, recent studies explore semantic representations to make CAM fit for WSSS and demonstrate encouraging results. However, they generally exploit single-level semantics, which may hamper the model to learn a comprehensive semantic structure. Motivated by the prior that each image has multiple levels of semantics, we propose hierarchical semantic contrast (HSC) to ameliorate the above problem. It conducts semantic contrast from coarse-grained to fine-grained perspective, including ROI level, class level, and pixel level, making the model learn a better object pattern understanding. To further improve CAM quality, building upon HSC, we explore consistency regularization of cross supervision and develop momentum prototype learning to utilize abundant semantics across different images. Extensive studies manifest that our plug-and-play learning paradigm, HSC, can significantly boost CAM quality on both non-saliency-guided and saliency-guided baselines, and establish new state-of-the-art WSSS performance on PASCAL VOC 2012 dataset. Code is available at https://github.com/Wu0409/HSC_WSSS.
7
Dai, Zhigang, Bolun Cai, and Junying Chen. "UniMoCo: Unsupervised, Semi-Supervised and Fully-Supervised Visual Representation Learning." In 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE, 2022. http://dx.doi.org/10.1109/smc53654.2022.9945500.
Full text
8
Wang, Yifeng, and Yi Zhao. "Scale and Direction Guided GAN for Inertial Sensor Signal Enhancement." In Thirty-Third International Joint Conference on Artificial Intelligence {IJCAI-24}. California: International Joint Conferences on Artificial Intelligence Organization, 2024. http://dx.doi.org/10.24963/ijcai.2024/567.
Full textAbstract:
Inertial sensors, serving as attitude and motion sensing components, are extensively used in various portable devices spanning consumer electronics, sports health, aerospace, etc. However, the severe intrinsic errors of inertial sensors greatly restrict their capability to implement advanced functions, such as motion tracking and semantic recognition. Although generative models hold significant potential for signal enhancement, unsupervised or weakly-supervised generative methods may not achieve ideal generation results due to the absence of guidance from paired data. To address this, we propose a scale and direction-guided generative adversarial network (SDG-GAN), which provides dual guidance mechanisms for GAN with unpaired data across two practical application scenarios. In the unsupervised scenario where only unpaired signals of varying quality are available, our scale-guided GAN (SG-GAN) forces the generator to learn high-quality signal characteristics at different scales simultaneously via the proposed self-supervised zoom constraint, thereby facilitating multi-scale interactive learning. In the weakly-supervised scenario, where additional experimental equipment can provide some motion information, our direction-guided GAN (DG-GAN) introduces auxiliary tasks to supervise signal generation while avoiding interference from auxiliary tasks on the main generation task. Extensive experiments demonstrate that both the unsupervised SG-GAN and the weakly-supervised DG-GAN significantly outperform all comparison methods, including fully-supervised approaches. The combined SDG-GAN achieves remarkable results, enabling unimaginable tasks based on the original inertial signal, such as 3D motion tracking.
9
Wang, Guanchun, Xiangrong Zhang, Zelin Peng, Xu Tang, Huiyu Zhou, and Licheng Jiao. "Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information." In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/192.
Full textAbstract:
Weakly supervised object detection (WSOD) is a challenging task, in which image-level labels (e.g., categories of the instances in the whole image) are used to train an object detector. Many existing methods follow the standard multiple instance learning (MIL) paradigm and have achieved promising performance. However, the lack of deterministic information leads to part domination and missing instances. To address these issues, this paper focuses on identifying and fully exploiting the deterministic information in WSOD. We discover that negative instances (i.e. absolutely wrong instances), ignored in most of the previous studies, normally contain valuable deterministic information. Based on this observation, we here propose a negative deterministic information (NDI) based method for improving WSOD, namely NDI-WSOD. Specifically, our method consists of two stages: NDI collecting and exploiting. In the collecting stage, we design several processes to identify and distill the NDI from negative instances online. In the exploiting stage, we utilize the extracted NDI to construct a novel negative contrastive learning mechanism and a negative guided instance selection strategy for dealing with the issues of part domination and missing instances, respectively. Experimental results on several public benchmarks including VOC 2007, VOC 2012 and MS COCO show that our method achieves satisfactory performance.
10
Pagé Fortin, Mathieu, and Brahim Chaib-draa. "Continual Semantic Segmentation Leveraging Image-level Labels and Rehearsal." In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/177.
Full textAbstract:
Despite the remarkable progress of deep learning models for semantic segmentation, the success of these models is strongly limited by the following aspects: 1) large datasets with pixel-level annotations must be available and 2) training must be performed with all classes simultaneously. Indeed, in incremental learning scenarios, where new classes are added to an existing framework, these models are prone to catastrophic forgetting of previous classes. To address these two limitations, we propose a weakly-supervised mechanism for continual semantic segmentation that can leverage cheap image-level annotations and a novel rehearsal strategy that intertwines the learning of past and new classes. Specifically, we explore two rehearsal technique variants: 1) imprinting past objects on new images and 2) transferring past representations in intermediate features maps. We conduct extensive experiments on Pascal-VOC by varying the proportion of fully- and weakly-supervised data in various setups and show that our contributions consistently improve the mIoU on both past and novel classes. Interestingly, we also observe that models trained with less data in incremental steps sometimes outperform the same architectures trained with more data. We discuss the significance of these results and propose some hypotheses regarding the dynamics between forgetting and learning.
Reports on the topic "Fully- and weakly-Supervised learning"
1
Nguyen, Minh H., Lorenzo Torresani, Fernando de la Torre, and Carsten Rother. Weakly Supervised Discriminative Localization and Classification: A Joint Learning Process. Fort Belvoir, VA: Defense Technical Information Center, July 2009. http://dx.doi.org/10.21236/ada507101.
Full text