NeurIPS 2020

Compositional Zero-Shot Learning via Fine-Grained Dense Feature Composition


Meta Review

Initially, this paper received diverging reviews. The reviewers found the idea interesting but had some concerns regarding clarity and the difference between the proposed method and the DAZLE baseline. The authors provided a rebuttal, clarifying the issues that were brought up by the reviews, which satisfied the reviewers. During the discussion, some reviewers have argued that the difference between DAZLE and the paper is clear, and the generated features have been demonstrated to have potential to identify new classes. All reviewers have rated the paper as positive (three "6:marginally above threshold" and one "7:accept") after the discussion phase, so overall the reviewers lean toward accepting. The AC concurs with this decision, and recommends acceptance as a poster. The authors are encouraged to update the paper using the material from the rebuttal to improve the issues brought up during the review, such as clarity.