LIP6 CNRS Sorbonne Université Tremplin Carnot Interfaces
Direct Link LIP6 » Tin tức » Nghiên cứu sinh
http://www.thomas-robert.fr

ROBERT Thomas

Tiến sĩ
Nhóm nghiên cứu : MLIA
Địa chỉ : Campus Pierre et Marie Curie
    Sorbonne Université - LIP6
    Boîte courrier 169
    Couloir 26-00, Étage 5, Bureau 525
    4 place Jussieu
    75252 PARIS CEDEX 05
    FRANCE
Tel: +33 1 44 27 51 29, Thomas.Robert (at) nulllip6.fr
http://www.thomas-robert.fr
Ban lãnh đạo nghiên cứu : Matthieu CORD
Đồng hướng dẫn : THOME Nicolas

Improving ConvNets Latent Representations for Visual Understanding

For a decade now, convolutional deep neural networks have demonstrated their ability to produce excellent results for computer vision. For this, these models transform the input image into a series of latent representations. In this thesis, we work on improving the ``quality'' of the latent representations of ConvNets for different tasks. First, we work on regularizing those representations to increase their robustness toward intra-class variations and thus improve their performance for classification. To do so, we develop a loss based on information theory metrics to decrease the entropy conditionally to the class. Then, we propose to structure the information in two complementary latent spaces, solving a conflict between the invariance of the representations and the reconstruction task. This structure allows to release the constraint posed by classical architecture, allowing to obtain better results in the context of semi-supervised learning. Finally, we address the problem of disentangling, i.e. explicitly separating and representing independent factors of variation of the dataset. We pursue our work on structuring the latent spaces and use adversarial costs to ensure an effective separation of the information. This allows to improve the quality of the representations and allows semantic image editing.
Bảo vệ luận án : 03-10-2019 - 14h - Campus Jussieu 55-65 211
Hội đồng giám khảo :
Stéphane Canu, INSA Rouen / LITIS [rapporteur]
Greg Mori, Simon Fraser University & Borealis AI [rapporteur]
Catherine Achard, Sorbonne Université / ISIR
Kartheek Alahari, Inria Grenoble / Thoth
David Picard, École nationale des ponts et chaussées / IMAGINE
Nicolas Thome, CNAM / CEDRIC
Matthieu Cord, Sorbonne Université / LIP6 & Valeo.ai

Bài báo khoa học 2010-2019

 Mentions légales
Sơ đồ site |