Bootstrap your own latent: A new approach to self-supervised Learning
This addresses the problem of learning effective visual representations without labeled data for computer vision tasks, offering a novel approach that outperforms existing methods.
The paper tackles self-supervised image representation learning by introducing BYOL, which achieves state-of-the-art performance without using negative pairs, reaching 74.3% top-1 accuracy on ImageNet with ResNet-50 and 79.6% with a larger ResNet.
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 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 a linear evaluation with a ResNet-50 architecture and $79.6\%$ 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. Our implementation and pretrained models are given on GitHub.