{"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/relation-networks-for-object-detection","title":"Relation Networks for Object Detection","arxiv_id":"1711.11575","date":"2017-11-30","proceeding":"CVPR 2018 6","authors":["Han Hu","Jiayuan Gu","Zheng Zhang","Jifeng Dai","Yichen Wei"],"abstract":"Although it is well believed for years that modeling relations between\nobjects would help object recognition, there has not been evidence that the\nidea is working in the deep learning era. All state-of-the-art object detection\nsystems still rely on recognizing object instances individually, without\nexploiting their relations during learning.\n  This work proposes an object relation module. It processes a set of objects\nsimultaneously through interaction between their appearance feature and\ngeometry, thus allowing modeling of their relations. It is lightweight and\nin-place. It does not require additional supervision and is easy to embed in\nexisting networks. It is shown effective on improving object recognition and\nduplicate removal steps in the modern object detection pipeline. It verifies\nthe efficacy of modeling object relations in CNN based detection. It gives rise\nto the first fully end-to-end object detector.","url_abs":"http://arxiv.org/abs/1711.11575v2","url_pdf":"http://arxiv.org/pdf/1711.11575v2.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":"relation-networks-for-object-detection","repo_url":"https://github.com/msracver/Relation-Networks-for-Object-Detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"relation-networks-for-object-detection","repo_url":"https://github.com/Asteur/relation-network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"relation-networks-for-object-detection","repo_url":"https://github.com/JunweiLiang/Object_Detection_Tracking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"relation-networks-for-object-detection","repo_url":"https://github.com/insigh/Relation_Network_for_Objection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"unanswered"}},{"paper_slug":"relation-networks-for-object-detection","repo_url":"https://github.com/jylins/core-text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"relation-networks-for-object-detection","repo_url":"https://github.com/super-wcg/Relation-Network-for-Object-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.11575","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}