Whitening Consistently Improves Self-Supervised Learning
This work addresses the need for universally applicable improvements in SSL for computer vision, though it is incremental as it builds on existing whitening techniques.
The study tackled the problem of enhancing self-supervised learning (SSL) by incorporating ZCA whitening as the final encoder layer, resulting in improved linear and k-NN probing accuracy by 1-5% across various SSL methods, architectures, and datasets.
Self-supervised learning (SSL) has been shown to be a powerful approach for learning visual representations. In this study, we propose incorporating ZCA whitening as the final layer of the encoder in self-supervised learning to enhance the quality of learned features by normalizing and decorrelating them. Although whitening has been utilized in SSL in previous works, its potential to universally improve any SSL model has not been explored. We demonstrate that adding whitening as the last layer of SSL pretrained encoders is independent of the self-supervised learning method and encoder architecture, thus it improves performance for a wide range of SSL methods across multiple encoder architectures and datasets. Our experiments show that whitening is capable of improving linear and k-NN probing accuracy by 1-5%. Additionally, we propose metrics that allow for a comprehensive analysis of the learned features, provide insights into the quality of the representations and help identify collapse patterns.