NeurIPS 2020

Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation

Meta Review

Four experts reviewed the paper. Three of them put the paper above the acceptance threshold, and one placed it marginally below. The reviewers were satisfied with the rebuttal in general, though R1 remained concerned about the technical novelty. Based on the reviewers' overall feedback, the decision is to recommend the paper for acceptance. The authors are encouraged to make the necessary changes to address the reviewers' questions to the best of their ability. Additionally, AC suggested reporting the results of both K=2 and K=3 due to their high silhouette scores. We congratulate the authors on the acceptance of their paper!