RepPoints V2: Verification Meets Regression for Object Detection

TL;DR

RepPoints V2 enhances object detection by integrating verification tasks into localization, leading to significant accuracy improvements over the original RepPoints and benefiting various detection frameworks.

Contribution

This paper introduces verification tasks into RepPoints for improved localization, achieving state-of-the-art results and demonstrating broader applicability.

Findings

About 2.0 mAP improvement over RepPoints on COCO

Achieves 52.1 mAP on COCO test-dev with a single model

Applicable to other detection frameworks and instance segmentation

Abstract

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 provides consistent improvements of about 2.0 mAP over the original RepPoints on the COCO object detection benchmark using different backbones and training methods. RepPoints v2 also achieves 52.1 mAP on 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. The code is available at https://github.com/Scalsol/RepPointsV2.