activity
20152024
most citedBootstrap your own latent: A new approach to self-supervised Learning

3.4k citations · 3.5k across the 7 of their papers we have counts for

collaborators

17 papers

cs.RO20241 cited

Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation

Homanga Bharadhwaj, Debidatta Dwibedi, Abhinav Gupta +7

How can robot manipulation policies generalize to novel tasks involving unseen object types and new motions? In this paper, we provide a solution in terms of predicting motion info…

cs.CV20225 cited

Kubric: A scalable dataset generator

Klaus Greff, Francois Belletti, Lucas Beyer +32

Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and trainin…

cs.CE202131 cited

Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs

Dan Rosenbaum, Marta Garnelo, Michal Zielinski +10

Cryo-electron microscopy (cryo-EM) has revolutionized experimental protein structure determination. Despite advances in high resolution reconstruction, a majority of cryo-EM experi…

cs.CV2020

CrossTransformers: spatially-aware few-shot transfer

Carl Doersch, Ankush Gupta, Andrew Zisserman

Given new tasks with very little datasuch as new classes in a classification problem or a domain shift in the inputperformance of modern vision systems degrades remarkably qu…

cs.LG20203.4k cited

Bootstrap your own latent: A new approach to self-supervised Learning

Jean-Bastien Grill, Florian Strub, Florent Altché +11

We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target…

cs.CV2019

Sim2real transfer learning for 3D human pose estimation: motion to the rescue

Carl Doersch, Andrew Zisserman

Synthetic visual data can provide practically infinite diversity and rich labels, while avoiding ethical issues with privacy and bias. However, for many tasks, current models train…