Supervision : Ludovic DENOYER

Co-supervision : ARTIÈRES Thierry

Learning with Weak Supervision Using Deep Generative Networks

Many successes of deep learning rely on the availability of massive annotated datasets that can be exploited by supervised algorithms. Obtaining those labels on 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 of 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.

2017-2020 Publications

• 2020
  • M. Chen : “Learning with Weak Supervision Using Deep Generative Networks”, thesis, phd defence 07/02/2020, supervision Denoyer, Ludovic, co-supervision : Artières, Thierry (2020)
  • J.‑Y. Franceschi, E. Delasalles, M. Chen, S. Lamprier, P. Gallinari : “Stochastic Latent Residual Video Prediction”, Proceedings of the 37^th International Conference on Machine Learning, vol. 119, Proceedings of Machine Learning Research, Vienne, Austria, pp. 3233-3246, (PMLR) (2020)
• 2019
  • M. Chen, Th. Artières, L. Denoyer : “Unsupervised Object Segmentation by Redrawing”, Advances in Neural Information Processing Systems 32 (NIPS 2019), Vancouver, Canada, pp. 12705-12716, (Curran Associates, Inc.) (2019)
• 2018
  • Th. Artières, Q. Wang, M. Chen, L. Denoyer : “Adversarial learning for modeling human motion”, The Visual Computer, pp. 1-20, (Springer Verlag) (2018)
  • M. Chen, L. Denoyer, Th. Artières : “Multi-View Data Generation Without View Supervision”, 6^th International Conference on Learning Representations (ICLR 2018), Vancouver, Canada (2018)
  • Q. Wang, M. Chen, Th. Artières, L. Denoyer : “Transferring Style in Motion Capture Sequences with Adversarial Learning”, ESANN, Bruges, Belgium (2018)
  • M. Chen, L. Denoyer, Th. Artières : “Multi-View Data Generation Without View Supervision”, (2018)
• 2017
  • M. Chen, L. Denoyer : “Multi-view Generative Adversarial Networks”, ECML PKDD 2017, vol. 10535, ECML PKDD 2017: Machine Learning and Knowledge Discovery in Databases, Skopje, North Macedonia, pp. 175-188 (2017)