This is the public, feature-limited version of the conference webpage. After Registration and login please visit the full version.

Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning

Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, koray kavukcuoglu, Remi Munos, Michal Valko

Oral presentation: Orals & Spotlights Track 27: Unsupervised/Probabilistic
on 2020-12-10T06:15:00-08:00 - 2020-12-10T06:30:00-08:00
Poster Session 6 (more posters)
on 2020-12-10T09:00:00-08:00 - 2020-12-10T11:00:00-08:00
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 predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network. While state-of-the art methods intrinsically rely on negative pairs, BYOL achieves a new state of the art without them. BYOL reaches 74.3% top-1 classification accuracy on ImageNet using the standard linear evaluation protocol with a standard ResNet-50 architecture and 79.6% with a larger ResNet. We also show that BYOL performs on par or better than the current state of the art on both transfer and semi-supervised benchmarks.

Preview Video and Chat

To see video, interact with the author and ask questions please use registration and login.