{"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/generalized-intersection-over-union-a-metric","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","arxiv_id":"1902.09630","date":"2019-02-25","proceeding":"CVPR 2019 6","authors":["Hamid Rezatofighi","Nathan Tsoi","JunYoung Gwak","Amir Sadeghian","Ian Reid","Silvio Savarese"],"abstract":"Intersection over Union (IoU) is the most popular evaluation metric used in\nthe object detection benchmarks. However, there is a gap between optimizing the\ncommonly used distance losses for regressing the parameters of a bounding box\nand maximizing this metric value. The optimal objective for a metric is the\nmetric itself. In the case of axis-aligned 2D bounding boxes, it can be shown\nthat $IoU$ can be directly used as a regression loss. However, $IoU$ has a\nplateau making it infeasible to optimize in the case of non-overlapping\nbounding boxes. In this paper, we address the weaknesses of $IoU$ by\nintroducing a generalized version as both a new loss and a new metric. By\nincorporating this generalized $IoU$ ($GIoU$) as a loss into the state-of-the\nart object detection frameworks, we show a consistent improvement on their\nperformance using both the standard, $IoU$ based, and new, $GIoU$ based,\nperformance measures on popular object detection benchmarks such as PASCAL VOC\nand MS COCO.","url_abs":"http://arxiv.org/abs/1902.09630v2","url_pdf":"http://arxiv.org/pdf/1902.09630v2.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":"generalized-intersection-over-union-a-metric","repo_url":"https://github.com/AnselmC/bamot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"generalized-intersection-over-union-a-metric","repo_url":"https://github.com/JaryHuang/awesome_SSD_FPN_GIoU","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generalized-intersection-over-union-a-metric","repo_url":"https://github.com/LinRiver/YOLOv3-on-LISA-Traffic-Sign-Detection-with-darknet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"generalized-intersection-over-union-a-metric","repo_url":"https://github.com/RuiminChen/GIou_loss_caffe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"generalized-intersection-over-union-a-metric","repo_url":"https://github.com/RuiminChen/GIouloss_CIouloss_caffe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"generalized-intersection-over-union-a-metric","repo_url":"https://github.com/gau-nernst/CenterNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generalized-intersection-over-union-a-metric","repo_url":"https://github.com/kalubin-awym/GIoU-loss-for-RetinaNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"generalized-intersection-over-union-a-metric","repo_url":"https://github.com/sremes/a2d2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"generalized-intersection-over-union-a-metric","repo_url":"https://github.com/OFRIN/Tensorflow_GIoU","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"generalized-intersection-over-union-a-metric","repo_url":"https://github.com/PaddlePaddle/PaddleDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.09630","atlas_url":"https://app.syntology.ai/?focus=1902.09630","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}