LIP6 CNRS Sorbonne Université Tremplin Carnot Interfaces
Direct Link LIP6 » News » PhD students

CHEN Mickael

PhD graduated
Team : MLIA
Localisation : Campus Pierre et Marie Curie
    Sorbonne Université - LIP6
    Boîte courrier 169
    Couloir 26-00, Étage 5, Bureau 513
    4 place Jussieu
    75252 PARIS CEDEX 05
    FRANCE
Tel: +33 1 44 27 88 07, Mickael.Chen (at) nulllip6.fr
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.
Defence : 07/02/2020 - 14h - Visioconférence
Jury members :
M. François Fleuret, Professeur, Université de Genève - EPFL [Rapporteur]
M. Jakob Verbeek, Directeur de Recherche - INRIA Grenoble - FAIR [Rapporteur]
M. Thierry Artières, Professeur, Aix Marseille Université - Ecole Centrale Marseille - LIS
M. Matthieu Cord, Professeur, Sorbonne Université - LIP6
M. Ludovic Denoyer, Professeur, Sorbonne Université - LIP6 - FAIR
Mme. Elisa Fromont, Professeur, Université de Rennes I - INRIA/IRISA

2017-2020 Publications

 Mentions légales
Site map |