Skip to Main content Skip to Navigation

Learning with weak supervision using deep generative networks

Abstract : Many successes of deep learning rely on the availability of massive annotated datasets that can be exploited by supervised algorithms. Obtaining those labels at a large scale, however, can be difficult, or even impossible in many situations. Designing methods that are less dependent on annotations is therefore a major research topic, and many semi-supervised and weakly supervised methods have been proposed. Meanwhile, the recent introduction of deep generative networks provided deep learning methods with the ability to manipulate complex distributions, allowing for breakthroughs in tasks such as image edition and domain adaptation. In this thesis, we explore how these new tools can be useful to further alleviate the need for annotations. Firstly, we tackle the task of performing stochastic predictions. It consists in designing systems for structured prediction that take into account the variability in possible outputs. We propose, in this context, two models. The first one performs predictions on multi-view data with missing views, and the second one predicts possible futures of a video sequence. Then, we study adversarial methods to learn a factorized latent space, in a setting with two explanatory factors but only one of them is annotated. We propose models that aim to uncover semantically consistent latent representations for those factors. One model is applied to the conditional generation of motion capture data, and another one to multi-view data. Finally, we focus on the task of image segmentation, which is of crucial importance in computer vision. Building on previously explored ideas, we propose a model for object segmentation that is entirely unsupervised.
Complete list of metadata
Contributor : ABES STAR :  Contact
Submitted on : Friday, February 26, 2021 - 11:32:44 AM
Last modification on : Saturday, July 9, 2022 - 3:21:16 AM
Long-term archiving on: : Thursday, May 27, 2021 - 6:21:56 PM


Version validated by the jury (STAR)


  • HAL Id : tel-03153266, version 1


Mickaël Chen. Learning with weak supervision using deep generative networks. Computer Vision and Pattern Recognition [cs.CV]. Sorbonne Université, 2020. English. ⟨NNT : 2020SORUS024⟩. ⟨tel-03153266⟩



Record views


Files downloads