Verification and regression are two general methodologies for prediction in neural networks. Each has its own strengths: verification can be easier to infer accurately, and regression is more efficient and applicable to continuous target variables. Hence, it is often beneficial to carefully combine them to take advantage of their benefits. In this paper, we take this philosophy to improve state-of-the-art object detection, specifically by RepPoints. Though RepPoints provides high performance, we find that its heavy reliance on regression for object localization leaves room for improvement. We introduce verification tasks into the localization prediction of RepPoints, producing RepPoints v2, which proves consistent improvements of about 2.0 mAP over the original RepPoints on COCO object detection benchmark using different backbones and training methods. RepPoints v2 also achieves 52.1 mAP on the COCO \texttt{test-dev} by a single model. Moreover, we show that the proposed approach can more generally elevate other object detection frameworks as well as applications such as instance segmentation.

It will be better to add more descriptions about RepPoints. It is hard for readers to follow the implementation details described in Sec 3.4 if they are not familiar with RepPoints. What is the meaning of "..., such that the first two points explicitly represent the top-left and bottom-right corner points." In my understanding, the authors still predict n sample points following RepPoints, but they adopt the first two points to do point-bbox transformation. I suggest the authors replace the description of "the first two points" with "the first two points in point sets R and R ". Describe the definition of RepPoints loss in the paper instead of appendix will make it more easy to understand the implementations.

The reviewers overall found merit in the main idea of this paper (introducing verification tasks in the setting of regression-based object detection). Overall, there is a good amount of analysis on differences between verification based methods as well as the introduction of a new method that does well. The reviewers found this work to be a good complement to RepPoints. I encourage the authors to take into account the feedback regarding the writing and the lack of some details for the final version of this work.

Verification and regression are two general methodologies for prediction in neural networks. Each has its own strengths: verification can be easier to infer accurately, and regression is more efficient and applicable to continuous target variables. Hence, it is often beneficial to carefully combine them to take advantage of their benefits. In this paper, we take this philosophy to improve state-of-the-art object detection, specifically by RepPoints. Though RepPoints provides high performance, we find that its heavy reliance on regression for object localization leaves room for improvement.