{"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/corner-proposal-network-for-anchor-free-two","title":"Corner Proposal Network for Anchor-free, Two-stage Object Detection","arxiv_id":"2007.13816","date":"2020-07-27","proceeding":"ECCV 2020 8","authors":["Kaiwen Duan","Lingxi Xie","Honggang Qi","Song Bai","Qingming Huang","Qi Tian"],"abstract":"The goal of object detection is to determine the class and location of objects in an image. This paper proposes a novel anchor-free, two-stage framework which first extracts a number of object proposals by finding potential corner keypoint combinations and then assigns a class label to each proposal by a standalone classification stage. We demonstrate that these two stages are effective solutions for improving recall and precision, respectively, and they can be integrated into an end-to-end network. Our approach, dubbed Corner Proposal Network (CPN), enjoys the ability to detect objects of various scales and also avoids being confused by a large number of false-positive proposals. On the MS-COCO dataset, CPN achieves an AP of 49.2% which is competitive among state-of-the-art object detection methods. CPN also fits the scenario of computational efficiency, which achieves an AP of 41.6%/39.7% at 26.2/43.3 FPS, surpassing most competitors with the same inference speed. Code is available at https://github.com/Duankaiwen/CPNDet","url_abs":"https://arxiv.org/abs/2007.13816v1","url_pdf":"https://arxiv.org/pdf/2007.13816v1.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":"corner-proposal-network-for-anchor-free-two","repo_url":"https://github.com/Duankaiwen/CPNDet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"adagrad","method_name":"AdaGrad"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"CPNDet (Hourglass-104, multi-scale)","rank_in_archive_order":98,"of":225,"metrics":{"AP50":"67.3","AP75":"53.7","APL":"62.4","APM":"51.9","APS":"31.0","box mAP":"49.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.13816","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}