https://hazyresearch.stanford.edu/blog/2022-04-19-contrastive-2
Improving Transfer and Robustness in Supervised Contrastive Learning
Apr 19, 2022
Mayee Chen, Dan Fu, Avanika Narayan, Michael Zhang, Zhao Song, Kayvon Fatahalian , and Chris Ré.
“A major problem in modern machine learning is how to learn good representations. Ideally, we’d like representations with good transferability and robustness. In this blog post, we look at how to achieve these properties for supervised contrastive learning…”