**Bootstrap Your Own Latent (BYOL)** is a novel approach to self-supervised image representation learning. Unlike state-of-the-art contrastive methods that rely on negative pairs, BYOL achieves superior performance without them. BYOL uses two neural networks, an *online* network and a *target* network, which interact and learn from each other. The online network is trained to predict the target network's representation of an augmented image, while the target network is updated with a slow-moving average of the online network. This method avoids the need for careful handling of negative pairs and is more robust to changes in image augmentations. BYOL achieves 74.3% top-1 classification accuracy on ImageNet using a linear evaluation with a ResNet-50 architecture and 79.6% with a larger ResNet. It outperforms current state-of-the-art methods on both transfer and semi-supervised benchmarks. The implementation and pre-trained models are available on GitHub.**Bootstrap Your Own Latent (BYOL)** is a novel approach to self-supervised image representation learning. Unlike state-of-the-art contrastive methods that rely on negative pairs, BYOL achieves superior performance without them. BYOL uses two neural networks, an *online* network and a *target* network, which interact and learn from each other. The online network is trained to predict the target network's representation of an augmented image, while the target network is updated with a slow-moving average of the online network. This method avoids the need for careful handling of negative pairs and is more robust to changes in image augmentations. BYOL achieves 74.3% top-1 classification accuracy on ImageNet using a linear evaluation with a ResNet-50 architecture and 79.6% with a larger ResNet. It outperforms current state-of-the-art methods on both transfer and semi-supervised benchmarks. The implementation and pre-trained models are available on GitHub.