activity
20172022
most citedMulti-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations

137 citations · 175 across the 8 of their papers we have counts for

collaborators

15 papers

cs.CV202211 cited

ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations

Badr Youbi Idrissi, Diane Bouchacourt, Randall Balestriero +7

Deep learning vision systems are widely deployed across applications where reliability is critical. However, even today's best models can fail to recognize an object when its pose,…

cs.CV20229 cited

The Robustness Limits of SoTA Vision Models to Natural Variation

Mark Ibrahim, Quentin Garrido, Ari Morcos +1

Recent state-of-the-art vision models introduced new architectures, learning paradigms, and larger pretraining data, leading to impressive performance on tasks such as classificati…

cs.CV20222 cited

Robust Self-Supervised Learning with Lie Groups

Mark Ibrahim, Diane Bouchacourt, Ari Morcos

Deep learning has led to remarkable advances in computer vision. Even so, today's best models are brittle when presented with variations that differ even slightly from those seen d…

cs.LG20215 cited

Addressing the Topological Defects of Disentanglement via Distributed Operators

Diane Bouchacourt, Mark Ibrahim, Stéphane Deny

A core challenge in Machine Learning is to learn to disentangle natural factors of variation in data (e.g. object shape vs. pose). A popular approach to disentanglement consists in…

cs.LG20209 cited

Think before you act: A simple baseline for compositional generalization

Christina Heinze-Deml, Diane Bouchacourt

Contrarily to humans who have the ability to recombine familiar expressions to create novel ones, modern neural networks struggle to do so. This has been emphasized recently with t…

cs.CL2020

Compositionality and Generalization in Emergent Languages

Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt +2

Natural language allows us to refer to novel composite concepts by combining expressions denoting their parts according to systematic rules, a property known as \emph{compositional…