@article{grill2020bootstrap,
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 per cent top-1 classification accuracy on ImageNet using the standard linear evaluation protocol with a ResNet-50 architecture and 79.6 per cent; with a larger ResNet. We show that BYOL performs on par or better than the current state of the art on both transfer and semi-supervised benchmarks.},
archivePrefix = {arXiv},
arxivId = {2006.07733},
author = {Grill, Jean-Bastien and Strub, Florian and Altch{\'{e}}, Florent and Tallec, Corentin and Richemond, Pierre H. and Buchatskaya, Elena and Doersch, Carl and Pires, Bernardo Avila and Guo, Zhaohan Daniel and Azar, Mohammad Gheshlaghi and Piot, Bilal and Kavukcuoglu, Koray and Munos, R{\'{e}}mi and Valko, Michal},
eprint = {2006.07733},
journal = {Neural Information Processing Systems},
title = {{Bootstrap your own latent: A new approach to self-supervised learning}},
year = {2020}
}