activity
20162026
most citedLearning Representations by Maximizing Mutual Information Across Views

677 citations · 915 across the 10 of their papers we have counts for

collaborators
Showing 2020Show all

6 papers · 1 filter

cs.CV2020

Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations

Tristan Sylvain, Linda Petrini, R Devon Hjelm

Zero-shot classification is a generalization task where no instance from the target classes is seen during training. To allow for test-time transfer, each class is annotated with s…

cs.LG2020

Implicit Regularization via Neural Feature Alignment

Aristide Baratin, Thomas George, César Laurent +4

We approach the problem of implicit regularization in deep learning from a geometrical viewpoint. We highlight a regularization effect induced by a dynamical alignment of the neura…

cs.CV202011 cited

Representation Learning with Video Deep InfoMax

R Devon Hjelm, Philip Bachman

Self-supervised learning has made unsupervised pretraining relevant again for difficult computer vision tasks. The most effective self-supervised methods involve prediction tasks b…

cs.LG2020

Deep Reinforcement and InfoMax Learning

Bogdan Mazoure, Remi Tachet des Combes, Thang Doan +2

We begin with the hypothesis that a model-free agent whose representations are predictive of properties of future states (beyond expected rewards) will be more capable of solving a…

cs.CV2020

Object-Centric Image Generation from Layouts

Tristan Sylvain, Pengchuan Zhang, Yoshua Bengio +2

Despite recent impressive results on single-object and single-domain image generation, the generation of complex scenes with multiple objects remains challenging. In this paper, we…

cs.LG2020

An end-to-end approach for the verification problem: learning the right distance

Joao Monteiro, Isabela Albuquerque, Jahangir Alam +2

In this contribution, we augment the metric learning setting by introducing a parametric pseudo-distance, trained jointly with the encoder. Several interpretations are thus drawn f…