activity
20172022
most citedWord Translation Without Parallel Data

249 citations · 607 across the 10 of their papers we have counts for

collaborators

16 papers

cs.CV2022

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…

cs.IR2022

Active Image Indexing

Pierre Fernandez, Matthijs Douze, Hervé Jégou +1

Image copy detection and retrieval from large databases leverage two components. First, a neural network maps an image to a vector representation, that is relatively robust to vari…

cs.CV2022

DeiT III: Revenge of the ViT

Hugo Touvron, Matthieu Cord, Hervé Jégou

A Vision Transformer (ViT) is a simple neural architecture amenable to serve several computer vision tasks. It has limited built-in architectural priors, in contrast to more recent…

cs.CV20228 cited

Three things everyone should know about Vision Transformers

Hugo Touvron, Matthieu Cord, Alaaeldin El-Nouby +2

After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks…

cs.CV202133 cited

ResNet strikes back: An improved training procedure in timm

Ross Wightman, Hugo Touvron, Hervé Jégou

The influential Residual Networks designed by He et al. remain the gold-standard architecture in numerous scientific publications. They typically serve as the default architecture…

cs.CV20216 cited

ResMLP: Feedforward networks for image classification with data-efficient training

Hugo Touvron, Piotr Bojanowski, Mathilde Caron +8

We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification. It is a simple residual network that alternates (i) a linear layer in which…