7fa215c9efebb3811a7ef58409907899-AuthorFeedback.pdf

We thank the reviewers for their time and insightful comments. We address the specific concerns and questions below. Sorry if it was not very clear in the paper. SimCLR with 65.7% in Table 1 is the original SimCLR The 1.4% accuracy gap is comparing 4-layer MLP versus Meanwhile, adding two more MLP layers can also help boost performance of GIM: 62.3% (Row 5) vs 60.9% The results match Fig.9 in the SimCLR paper which shows We also include results trained with 800 epochs in the Supp.