3 code implementations • 28 Sep 2023 • Timothée Darcet, Maxime Oquab, Julien Mairal, Piotr Bojanowski
Transformers have recently emerged as a powerful tool for learning visual representations.
11 code implementations • 14 Apr 2023 • Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mahmoud Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Hervé Jegou, Julien Mairal, Patrick Labatut, Armand Joulin, Piotr Bojanowski
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.
Ranked #1 on Image Classification on CIFAR-10 (using extra training data)
1 code implementation • CVPR 2023 • Hugo Touvron, Matthieu Cord, Maxime Oquab, Piotr Bojanowski, Jakob Verbeek, Hervé Jégou
Given a neural network to be trained, for each sample we implicitly instantiate two altered networks, "submodels", with stochastic depth: i. e. activating only a subset of the layers and skipping others.
1 code implementation • 9 Dec 2022 • Hugo Touvron, Matthieu Cord, Maxime Oquab, Piotr Bojanowski, Jakob Verbeek, Hervé Jégou
We introduce submodel co-training, a regularization method related to co-training, self-distillation and stochastic depth.
Ranked #69 on Image Classification on ImageNet
no code implementations • 16 Mar 2022 • Maxime Oquab, Daniel Haziza, Ludovic Schwartz, Tao Xu, Katayoun Zand, Rui Wang, Peirong Liu, Camille Couprie
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 realism.
no code implementations • 6 Jan 2021 • Yair Lakretz, Théo Desbordes, Jean-Rémi King, Benoît Crabbé, Maxime Oquab, Stanislas Dehaene
Finally, probing the internal states of the model during the processing of sentences with nested tree structures, we found a complex encoding of grammatical agreement information (e. g. grammatical number), in which all the information for multiple words nouns was carried by a single unit.
no code implementations • 1 Dec 2020 • Maxime Oquab, Pierre Stock, Oran Gafni, Daniel Haziza, Tao Xu, Peizhao Zhang, Onur Celebi, Yana Hasson, Patrick Labatut, Bobo Bose-Kolanu, Thibault Peyronel, Camille Couprie
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 device using facial landmarks extracted at the sender's side and transmitted over the network.
no code implementations • 25 Sep 2019 • Jean-Remi King, Francois Charton, Maxime Oquab, David Lopez-Paz
Identifying causes from observations can be particularly challenging when i) potential factors are difficult to manipulate individually and ii) observations are complex and multi-dimensional.
1 code implementation • NeurIPS 2019 • Mohamed Ishmael Belghazi, Maxime Oquab, Yann Lecun, David Lopez-Paz
We introduce the Neural Conditioner (NC), a self-supervised machine able to learn about all the conditional distributions of a random vector $X$.
no code implementations • 21 Dec 2017 • Leon Bottou, Martin Arjovsky, David Lopez-Paz, Maxime Oquab
Learning algorithms for implicit generative models can optimize a variety of criteria that measure how the data distribution differs from the implicit model distribution, including the Wasserstein distance, the Energy distance, and the Maximum Mean Discrepancy criterion.
1 code implementation • 20 Oct 2016 • David Lopez-Paz, Maxime Oquab
The goal of this paper is to establish the properties, performance, and uses of C2ST.
1 code implementation • 14 Sep 2016 • Vadim Kantorov, Maxime Oquab, Minsu Cho, Ivan Laptev
The additive model encourages the predicted object region to be supported by its surrounding context region.
Ranked #4 on Weakly Supervised Object Detection on Charades
no code implementations • CVPR 2015 • Maxime Oquab, Leon Bottou, Ivan Laptev, Josef Sivic
Successful visual object recognition methods typically rely on training datasets containing lots of richly annotated images.
1 code implementation • CVPR 2014 • Maxime Oquab, Leon Bottou, Ivan Laptev, Josef Sivic
We show that despite differences in image statistics and tasks in the two datasets, the transferred representation leads to significantly improved results for object and action classification, outperforming the current state of the art on Pascal VOC 2007 and 2012 datasets.