NeurIPS 2020

Supervised Contrastive Learning

Meta Review

Four knowledgeable reviewers support acceptance for the contributions. Reviewers find the paper well-written and appreciate the strong empirical results by proposing a loss function that can form multiple positive and negative pairs for each anchor in a minibatch, leading to more effective training. Therefore, I also recommend acceptance. However, please consider revising your paper to address all the concerns and comments from the reviewers.