activity
20192022
most citedEqui-normalization of Neural Networks

3 citations · 6 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG20223 cited

Defending against Reconstruction Attacks with Rényi Differential Privacy

Pierre Stock, Igor Shilov, Ilya Mironov +1

Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model. It has been recently shown that simple heuristics can…

cs.CV2021

LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference

Ben Graham, Alaaeldin El-Nouby, Hugo Touvron +4

We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime. Our work exploits recent findings in at…

cs.CV2020

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…

cs.LG2020

Training with Quantization Noise for Extreme Model Compression

Angela Fan, Pierre Stock, Benjamin Graham +4

We tackle the problem of producing compact models, maximizing their accuracy for a given model size. A standard solution is to train networks with Quantization Aware Training, wher…

cs.CV2019

And the Bit Goes Down: Revisiting the Quantization of Neural Networks

Pierre Stock, Armand Joulin, Rémi Gribonval +2

In this paper, we address the problem of reducing the memory footprint of convolutional network architectures. We introduce a vector quantization method that aims at preserving the…

cs.CV20193 cited

Equi-normalization of Neural Networks

Pierre Stock, Benjamin Graham, Rémi Gribonval +1

Modern neural networks are over-parametrized. In particular, each rectified linear hidden unit can be modified by a multiplicative factor by adjusting input and output weights, wit…