{"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/noh-nms-improving-pedestrian-detection-by","title":"NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination","arxiv_id":"2007.13376","date":"2020-07-27","proceeding":null,"authors":["Penghao Zhou","Chong Zhou","Pai Peng","Junlong Du","Xing Sun","Xiaowei Guo","Feiyue Huang"],"abstract":"Greedy-NMS inherently raises a dilemma, where a lower NMS threshold will potentially lead to a lower recall rate and a higher threshold introduces more false positives. This problem is more severe in pedestrian detection because the instance density varies more intensively. However, previous works on NMS don't consider or vaguely consider the factor of the existent of nearby pedestrians. Thus, we propose Nearby Objects Hallucinator (NOH), which pinpoints the objects nearby each proposal with a Gaussian distribution, together with NOH-NMS, which dynamically eases the suppression for the space that might contain other objects with a high likelihood. Compared to Greedy-NMS, our method, as the state-of-the-art, improves by $3.9\\%$ AP, $5.1\\%$ Recall, and $0.8\\%$ $\\text{MR}^{-2}$ on CrowdHuman to $89.0\\%$ AP and $92.9\\%$ Recall, and $43.9\\%$ $\\text{MR}^{-2}$ respectively.","url_abs":"https://arxiv.org/abs/2007.13376v1","url_pdf":"https://arxiv.org/pdf/2007.13376v1.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":"noh-nms-improving-pedestrian-detection-by","repo_url":"https://github.com/TencentYoutuResearch/PedestrianDetection-NohNMS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"pedestrian-detection","task_name":"Pedestrian Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-crowdhuman-full-body","task":"Object Detection","dataset":"CrowdHuman (full body)","model":"NOH-NMS","rank_in_archive_order":13,"of":19,"metrics":{"AP":"89.0","mMR":"43.9"},"uses_additional_data":false},{"leaderboard":"/sota/pedestrian-detection-on-citypersons","task":"Pedestrian Detection","dataset":"CityPersons","model":"NOH-NMS","rank_in_archive_order":13,"of":22,"metrics":{"Bare MR^-2":"6.6","Heavy MR^-2":"53.0","Partial MR^-2":"11.2","Reasonable MR^-2":"10.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.13376","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}