NeurIPS 2020

Soft Contrastive Learning for Visual Localization

Meta Review

The initial scores for this paper were: 5: Marginally below the acceptance threshold. 7: A good submission; accept. 7: A good submission; accept. 7: A good submission; accept. Reviewers are overall positive but raise issues regarding clarity of explanation, missing discussion, some missing ablations, and some missing analysis of the results. The main issue raised by R4 (5) is regarding the need and the justification of the theoretical part of the paper. The authors provide a rebuttal. In the post-rebuttal discussion, R4 raises their score from 5 to 7 but their issue regarding the theoretical section of the paper partly remains. The final scores of the paper are 7, 7, 7, 7. The reviewers provide final comments after seeing the rebuttal in their reviews. The AC is convinced by the positive arguments of the reviewers and recommends Accept. The authors are strongly encouraged to take into account all reviewers' feedback (and especially the remaining comments mentioned by R4) when preparing the final version.