activity
20162023
most citedDINOv2: Learning Robust Visual Features without Supervision

1.1k citations · 1.6k across the 15 of their papers we have counts for

collaborators
Showing cs.LGShow all

13 papers · 1 filter

cs.LG2023★ 2 cited

A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation

Florian Bordes, Samuel Lavoie, Randall Balestriero +2

Self-Supervised Learning (SSL) models rely on a pretext task to learn representations. Because this pretext task differs from the downstream tasks used to evaluate the performance…

cs.LG2022

Uniform Masking Prevails in Vision-Language Pretraining

Siddharth Verma, Yuchen Lu, Rui Hou +4

Masked Language Modeling (MLM) has proven to be an essential component of Vision-Language (VL) pretraining. To implement MLM, the researcher must make two design choices: the maski…

cs.LG2022

Neural Attentive Circuits

Nasim Rahaman, Martin Weiss, Francesco Locatello +5

Recent work has seen the development of general purpose neural architectures that can be trained to perform tasks across diverse data modalities. General purpose models typically m…

cs.LG2022★ 13 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.LG2022★ 8 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.LG2021

Trade-offs of Local SGD at Scale: An Empirical Study

Jose Javier Gonzalez Ortiz, Jonathan Frankle, Mike Rabbat +2

As datasets and models become increasingly large, distributed training has become a necessary component to allow deep neural networks to train in reasonable amounts of time. Howeve…