555 citations · 1.7k across the 35 of their papers we have counts for
37 papers
On the Identifiability of Quantized Factors
Vitória Barin-Pacela, Kartik Ahuja, Simon Lacoste-Julien +1
Disentanglement aims to recover meaningful latent ground-truth factors from the observed distribution solely, and is formalized through the theory of identifiability. The identifia…
Objectives Matter: Understanding the Impact of Self-Supervised Objectives on Vision Transformer Representations
Shashank Shekhar, Florian Bordes, Pascal Vincent +1
Joint-embedding based learning (e.g., SimCLR, MoCo, DINO) and reconstruction-based learning (e.g., BEiT, SimMIM, MAE) are the two leading paradigms for self-supervised learning of…
A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation
Florian Bordes, Samuel Lavoie, Randall Balestriero +2
Self-Supervised Learning (SSL) models rely on a pretext task to learn representations. Because this pretext task differs from the downstream tasks used to evaluate the performance…
Instance-Conditioned GAN Data Augmentation for Representation Learning
Pietro Astolfi, Arantxa Casanova, Jakob Verbeek +3
Data augmentation has become a crucial component to train state-of-the-art visual representation models. However, handcrafting combinations of transformations that lead to improved…
Towards Democratizing Joint-Embedding Self-Supervised Learning
Florian Bordes, Randall Balestriero, Pascal Vincent
Joint Embedding Self-Supervised Learning (JE-SSL) has seen rapid developments in recent years, due to its promise to effectively leverage large unlabeled data. The development of J…
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,…