{"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/disentangle-your-dense-object-detector","title":"Disentangle Your Dense Object Detector","arxiv_id":"2107.02963","date":"2021-07-07","proceeding":null,"authors":["Zehui Chen","Chenhongyi Yang","Qiaofei Li","Feng Zhao","Zheng-Jun Zha","Feng Wu"],"abstract":"Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors is compromised to lots of conjunctions that may not hold. In this paper, we investigate three such important conjunctions: 1) only samples assigned as positive in classification head are used to train the regression head; 2) classification and regression share the same input feature and computational fields defined by the parallel head architecture; and 3) samples distributed in different feature pyramid layers are treated equally when computing the loss. We first carry out a series of pilot experiments to show disentangling such conjunctions can lead to persistent performance improvement. Then, based on these findings, we propose Disentangled Dense Object Detector (DDOD), in which simple and effective disentanglement mechanisms are designed and integrated into the current state-of-the-art dense object detectors. Extensive experiments on MS COCO benchmark show that our approach can lead to 2.0 mAP, 2.4 mAP and 2.2 mAP absolute improvements on RetinaNet, FCOS, and ATSS baselines with negligible extra overhead. Notably, our best model reaches 55.0 mAP on the COCO test-dev set and 93.5 AP on the hard subset of WIDER FACE, achieving new state-of-the-art performance on these two competitive benchmarks. Code is available at https://github.com/zehuichen123/DDOD.","url_abs":"https://arxiv.org/abs/2107.02963v2","url_pdf":"https://arxiv.org/pdf/2107.02963v2.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":"disentangle-your-dense-object-detector","repo_url":"https://github.com/zehuichen123/DDOD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"disentangle-your-dense-object-detector","repo_url":"https://github.com/open-mmlab/mmdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"object","task_name":"Object"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"atss","method_name":"ATSS"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fcos","method_name":"FCOS"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"focal-loss","method_name":"Focal Loss"},{"method_slug":"non-maximum-suppression","method_name":"Non Maximum Suppression"},{"method_slug":"retinanet","method_name":"RetinaNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.02963","atlas_url":"https://app.syntology.ai/?focus=2107.02963","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":"2107.02963"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2107.02963\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2107.02963"},"call":"get_concepts_for_paper(arxiv_id=\"2107.02963\")"}],"by_repo":[{"repo":"zehuichen123/DDOD","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"open-mmlab/mmdetection","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2401.02361"],"harvested_for_calls":[{"arxiv_id":"2401.02361","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2401.02361"},"call":"get_harvested_code_for_paper(arxiv_id=\"2401.02361\")"}]}],"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":"75283330024d6a9011f23eee0d02b96fbfcd2e6f5ff60f471c358e2660f5a818","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}