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

Grill, Jean-Bastien; Strub, Florian; Altché, Florent; Tallec, Corentin; H. Richemond, Pierre; Buchatskaya, Elena; Doersch, Carl; Ávila Pires, Bernardo; Daniel Guo, Zhaohan; Gheshlaghi Azar, Mohammad; Piot, Bilal; Kavukcuoglu, Koray; Munos, Rémi; Valko, Michal

doi:10.48550/arxiv.2006.07733

Public

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

Published in arXiv (Cornell University) • Jun 13, 2020

Authors:

Jean-Bastien Grill

Florian Strub

Florent Altché

Abstract

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 networks, that interact and learn from each other. From an augmented view of an image, we train the online network to p...

Subject

Computer science

Artificial intelligence

Machine learning

Research Assistant

AI chat, annotations, notes & similar papers

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!