{"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/progressive-end-to-end-object-detection-in","title":"Progressive End-to-End Object Detection in Crowded Scenes","arxiv_id":"2203.07669","date":"2022-03-15","proceeding":"CVPR 2022 1","authors":["Anlin Zheng","Yuang Zhang","Xiangyu Zhang","Xiaojuan Qi","Jian Sun"],"abstract":"In this paper, we propose a new query-based detection framework for crowd detection. Previous query-based detectors suffer from two drawbacks: first, multiple predictions will be inferred for a single object, typically in crowded scenes; second, the performance saturates as the depth of the decoding stage increases. Benefiting from the nature of the one-to-one label assignment rule, we propose a progressive predicting method to address the above issues. Specifically, we first select accepted queries prone to generate true positive predictions, then refine the rest noisy queries according to the previously accepted predictions. Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes. Equipped with our approach, Sparse RCNN achieves 92.0\\% $\\text{AP}$, 41.4\\% $\\text{MR}^{-2}$ and 83.2\\% $\\text{JI}$ on the challenging CrowdHuman \\cite{shao2018crowdhuman} dataset, outperforming the box-based method MIP \\cite{chu2020detection} that specifies in handling crowded scenarios. Moreover, the proposed method, robust to crowdedness, can still obtain consistent improvements on moderately and slightly crowded datasets like CityPersons \\cite{zhang2017citypersons} and COCO \\cite{lin2014microsoft}. Code will be made publicly available at https://github.com/megvii-model/Iter-E2EDET.","url_abs":"https://arxiv.org/abs/2203.07669v3","url_pdf":"https://arxiv.org/pdf/2203.07669v3.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":"progressive-end-to-end-object-detection-in","repo_url":"https://github.com/megvii-model/iter-e2edet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"progressive-end-to-end-object-detection-in","repo_url":"https://github.com/zyayoung/Iter-Deformable-DETR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-crowdhuman","task":"Object Detection","dataset":"CrowdHuman","model":"S-RCNN+Ours","rank_in_archive_order":1,"of":1,"metrics":{"AP":"92.5","MR^-2":"41.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-crowdhuman-full-body","task":"Object Detection","dataset":"CrowdHuman (full body)","model":"Progressive DETR","rank_in_archive_order":3,"of":19,"metrics":{"AP":"94.1","mMR":"37.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.07669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07669"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/megvii-model/Iter-E2EDET","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"0009e0d4199fc9d2","entry":"RelationNet","repo":"megvii-model/Iter-E2EDET","repo_kind":"official","path":"projects/crowd-e2e-sparse-rcnn/models/relation_net.py","file_url":"https://github.com/megvii-model/Iter-E2EDET/blob/HEAD/projects/crowd-e2e-sparse-rcnn/models/relation_net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0009e0d4199fc9d2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}