{"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/location-sensitive-visual-recognition-with","title":"Location-Sensitive Visual Recognition with Cross-IOU Loss","arxiv_id":"2104.04899","date":"2021-04-11","proceeding":null,"authors":["Kaiwen Duan","Lingxi Xie","Honggang Qi","Song Bai","Qingming Huang","Qi Tian"],"abstract":"Object detection, instance segmentation, and pose estimation are popular visual recognition tasks which require localizing the object by internal or boundary landmarks. This paper summarizes these tasks as location-sensitive visual recognition and proposes a unified solution named location-sensitive network (LSNet). Based on a deep neural network as the backbone, LSNet predicts an anchor point and a set of landmarks which together define the shape of the target object. The key to optimizing the LSNet lies in the ability of fitting various scales, for which we design a novel loss function named cross-IOU loss that computes the cross-IOU of each anchor point-landmark pair to approximate the global IOU between the prediction and ground-truth. The flexibly located and accurately predicted landmarks also enable LSNet to incorporate richer contextual information for visual recognition. Evaluated on the MS-COCO dataset, LSNet set the new state-of-the-art accuracy for anchor-free object detection (a 53.5% box AP) and instance segmentation (a 40.2% mask AP), and shows promising performance in detecting multi-scale human poses. Code is available at https://github.com/Duankaiwen/LSNet","url_abs":"https://arxiv.org/abs/2104.04899v1","url_pdf":"https://arxiv.org/pdf/2104.04899v1.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":"location-sensitive-visual-recognition-with","repo_url":"https://github.com/Duankaiwen/LSNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"LSNet (Res2Net-101+ DCN, multi-scale)","rank_in_archive_order":61,"of":225,"metrics":{"AP50":"71.1","AP75":"59.2","APL":"65.8","APM":"56.4","APS":"35.2","box mAP":"53.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.04899","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}