{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/generalized-focal-loss-v2-learning-reliable","title":"Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection","arxiv_id":"2011.12885","date":"2020-11-25","proceeding":"CVPR 2021 1","authors":["Xiang Li","Wenhai Wang","Xiaolin Hu","Jun Li","Jinhui Tang","Jian Yang"],"abstract":"Localization Quality Estimation (LQE) is crucial and popular in the recent advancement of dense object detectors since it can provide accurate ranking scores that benefit the Non-Maximum Suppression processing and improve detection performance. As a common practice, most existing methods predict LQE scores through vanilla convolutional features shared with object classification or bounding box regression. In this paper, we explore a completely novel and different perspective to perform LQE -- based on the learned distributions of the four parameters of the bounding box. The bounding box distributions are inspired and introduced as \"General Distribution\" in GFLV1, which describes the uncertainty of the predicted bounding boxes well. Such a property makes the distribution statistics of a bounding box highly correlated to its real localization quality. Specifically, a bounding box distribution with a sharp peak usually corresponds to high localization quality, and vice versa. By leveraging the close correlation between distribution statistics and the real localization quality, we develop a considerably lightweight Distribution-Guided Quality Predictor (DGQP) for reliable LQE based on GFLV1, thus producing GFLV2. To our best knowledge, it is the first attempt in object detection to use a highly relevant, statistical representation to facilitate LQE. Extensive experiments demonstrate the effectiveness of our method. Notably, GFLV2 (ResNet-101) achieves 46.2 AP at 14.6 FPS, surpassing the previous state-of-the-art ATSS baseline (43.6 AP at 14.6 FPS) by absolute 2.6 AP on COCO {\\tt test-dev}, without sacrificing the efficiency both in training and inference. Code will be available at https://github.com/implus/GFocalV2.","url_abs":"https://arxiv.org/abs/2011.12885v1","url_pdf":"https://arxiv.org/pdf/2011.12885v1.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-focal-loss-v2-learning-reliable","repo_url":"https://github.com/implus/GFocalV2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"generalized-focal-loss-v2-learning-reliable","repo_url":"https://github.com/Edwardwaw/gfocalv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"generalized-focal-loss-v2-learning-reliable","repo_url":"https://github.com/CV51GO/GFLv2_Megengine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"generalized-focal-loss-v2-learning-reliable","repo_url":"https://github.com/PaddlePaddle/PaddleDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"generalized-focal-loss-v2-learning-reliable","repo_url":"https://github.com/shinya7y/UniverseNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"dense-object-detection","task_name":"Dense Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"atss","method_name":"ATSS"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"GFLV2 (Res2Net-101, DCN, multiscale)","rank_in_archive_order":66,"of":225,"metrics":{"AP50":"70.9","AP75":"59.2","APL":"65.6","APM":"56.1","APS":"35.7","box mAP":"53.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"GFLV2 (Res2Net-101, DCN)","rank_in_archive_order":89,"of":225,"metrics":{"AP50":"69","AP75":"55.3","APL":"63.5","APM":"54.3","APS":"31.3","box mAP":"50.6"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"GFLV2 (ResNeXt-101, 32x4d, DCN)","rank_in_archive_order":99,"of":225,"metrics":{"AP50":"67.6","AP75":"53.5","APL":"61.4","APM":"52.4","APS":"29.7","Hardware Burden":"3G","box mAP":"49"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"GFLV2 (ResNet-101-DCN)","rank_in_archive_order":107,"of":225,"metrics":{"AP50":"66.5","AP75":"52.8","APL":"60.7","APM":"51.9","APS":"28.8","Hardware Burden":"3G","box mAP":"48.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"GFLV2 (ResNet-101)","rank_in_archive_order":128,"of":225,"metrics":{"AP50":"64.3","AP75":"50.5","APL":"57","APM":"49.9","APS":"27.8","box mAP":"46.2"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"GFLV2 (ResNet-50)","rank_in_archive_order":148,"of":225,"metrics":{"AP50":"62.3","AP75":"48.5","APL":"54.1","APM":"47.7","APS":"26.8","box mAP":"44.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-o","task":"Object Detection","dataset":"COCO-O","model":"GFLv2\n(R2-101-DCN)","rank_in_archive_order":26,"of":45,"metrics":{"Average mAP":"25.1","Effective Robustness":"2.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.12885","atlas_url":"https://app.syntology.ai/?focus=2011.12885","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2011.12885"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2011.12885\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2011.12885"},"call":"get_concepts_for_paper(arxiv_id=\"2011.12885\")"}],"by_repo":[{"repo":"implus/GFocalV2","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Edwardwaw/gfocalv2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"CV51GO/GFLv2_Megengine","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"PaddlePaddle/PaddleDetection","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2203.16250"],"harvested_for_calls":[{"arxiv_id":"2203.16250","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.16250"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.16250\")"}]},{"repo":"shinya7y/UniverseNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9aa82145da7048b3b3eecb49645123e56895b62a95af20ffdb7da9801ece76fb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}