{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/reppoints-v2-verification-meets-regression","title":"RepPoints V2: Verification Meets Regression for Object Detection","arxiv_id":"2007.08508","date":"2020-07-16","proceeding":"NeurIPS 2020 12","authors":["Yihong Chen","Zheng Zhang","Yue Cao","Li-Wei Wang","Stephen Lin","Han Hu"],"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.","url_abs":"https://arxiv.org/abs/2007.08508v1","url_pdf":"https://arxiv.org/pdf/2007.08508v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"reppoints-v2-verification-meets-regression","repo_url":"https://github.com/Scalsol/RepPointsV2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"philosophy","task_name":"Philosophy"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"reppoints","method_name":"RepPoints"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"RepPoints v2 (ResNeXt-101, DCN, multi-scale)","rank_in_archive_order":75,"of":225,"metrics":{"AP50":"70.1","AP75":"57.5","APL":"63.6","APM":"54.6","APS":"34.5","box mAP":"52.1"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"RepPoints v2 (ResNeXt-101, DCN)","rank_in_archive_order":95,"of":225,"metrics":{"AP50":"68.9","AP75":"53.4","APL":"62.3","APM":"52.1","APS":"30.3","box mAP":"49.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-o","task":"Object Detection","dataset":"COCO-O","model":"RepPointsV2\n(RX-101-64x4d-DCN)","rank_in_archive_order":27,"of":45,"metrics":{"Average mAP":"24.9","Effective Robustness":"2.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.08508","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}