activity
20182022
most citedThe Hidden Uniform Cluster Prior in Self-Supervised Learning

13 citations · 21 across the 2 of their papers we have counts for

collaborators

8 papers

cs.LG202213 cited

The Hidden Uniform Cluster Prior in Self-Supervised Learning

Mahmoud Assran, Randall Balestriero, Quentin Duval +6

A successful paradigm in representation learning is to perform self-supervised pretraining using tasks based on mini-batch statistics (e.g., SimCLR, VICReg, SwAV, MSN). We show tha…

cs.LG20228 cited

Masked Siamese Networks for Label-Efficient Learning

Mahmoud Assran, Mathilde Caron, Ishan Misra +6

We propose Masked Siamese Networks (MSN), a self-supervised learning framework for learning image representations. Our approach matches the representation of an image view containi…

cs.CV2021

Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples

Mahmoud Assran, Mathilde Caron, Ishan Misra +4

This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures t…

cs.LG2020

A Closer Look at Codistillation for Distributed Training

Shagun Sodhani, Olivier Delalleau, Mahmoud Assran +3

Codistillation has been proposed as a mechanism to share knowledge among concurrently trained models by encouraging them to represent the same function through an auxiliary loss. T…

cs.LG2020

Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations

Mahmoud Assran, Nicolas Ballas, Lluis Castrejon +1

We investigate a strategy for improving the efficiency of contrastive learning of visual representations by leveraging a small amount of supervised information during pre-training.…

cs.LG2020

On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings

Mahmoud Assran, Michael Rabbat

We study Nesterov's accelerated gradient method with constant step-size and momentum parameters in the stochastic approximation setting (unbiased gradients with bounded variance) a…