1.1k citations · 1.2k across the 7 of their papers we have counts for
9 papers
DINOv2: Learning Robust Visual Features without Supervision
Maxime Oquab, Timothée Darcet, Théo Moutakanni +23
The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. Thes…
Co-training Submodels for Visual Recognition
Hugo Touvron, Matthieu Cord, Maxime Oquab +3
We introduce submodel co-training, a regularization method related to co-training, self-distillation and stochastic depth. Given a neural network to be trained, for each sample we…
Efficient conditioned face animation using frontally-viewed embedding
Maxime Oquab, Daniel Haziza, Ludovic Schwartz +5
As the quality of few shot facial animation from landmarks increases, new applications become possible, such as ultra low bandwidth video chat compression with a high degree of rea…
Can RNNs learn Recursive Nested Subject-Verb Agreements?
Yair Lakretz, Théo Desbordes, Jean-Rémi King +3
One of the fundamental principles of contemporary linguistics states that language processing requires the ability to extract recursively nested tree structures. However, it remain…
Low Bandwidth Video-Chat Compression using Deep Generative Models
Maxime Oquab, Pierre Stock, Oran Gafni +9
To unlock video chat for hundreds of millions of people hindered by poor connectivity or unaffordable data costs, we propose to authentically reconstruct faces on the receiver's de…
Learning about an exponential amount of conditional distributions
Mohamed Ishmael Belghazi, Maxime Oquab, Yann LeCun +1
We introduce the Neural Conditioner (NC), a self-supervised machine able to learn about all the conditional distributions of a random vector . The NC is a function $NC(x \cdot a…