{"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/soft-nms-improving-object-detection-with-one","title":"Soft-NMS -- Improving Object Detection With One Line of Code","arxiv_id":"1704.04503","date":"2017-04-14","proceeding":"ICCV 2017 10","authors":["Navaneeth Bodla","Bharat Singh","Rama Chellappa","Larry S. Davis"],"abstract":"Non-maximum suppression is an integral part of the object detection pipeline.\nFirst, it sorts all detection boxes on the basis of their scores. The detection\nbox M with the maximum score is selected and all other detection boxes with a\nsignificant overlap (using a pre-defined threshold) with M are suppressed. This\nprocess is recursively applied on the remaining boxes. As per the design of the\nalgorithm, if an object lies within the predefined overlap threshold, it leads\nto a miss. To this end, we propose Soft-NMS, an algorithm which decays the\ndetection scores of all other objects as a continuous function of their overlap\nwith M. Hence, no object is eliminated in this process. Soft-NMS obtains\nconsistent improvements for the coco-style mAP metric on standard datasets like\nPASCAL VOC 2007 (1.7% for both R-FCN and Faster-RCNN) and MS-COCO (1.3% for\nR-FCN and 1.1% for Faster-RCNN) by just changing the NMS algorithm without any\nadditional hyper-parameters. Using Deformable-RFCN, Soft-NMS improves\nstate-of-the-art in object detection from 39.8% to 40.9% with a single model.\nFurther, the computational complexity of Soft-NMS is the same as traditional\nNMS and hence it can be efficiently implemented. Since Soft-NMS does not\nrequire any extra training and is simple to implement, it can be easily\nintegrated into any object detection pipeline. Code for Soft-NMS is publicly\navailable on GitHub (http://bit.ly/2nJLNMu).","url_abs":"http://arxiv.org/abs/1704.04503v2","url_pdf":"http://arxiv.org/pdf/1704.04503v2.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":"soft-nms-improving-object-detection-with-one","repo_url":"https://github.com/Iqbal1282/YoloV3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"soft-nms-improving-object-detection-with-one","repo_url":"https://github.com/ZFTurbo/Weighted-Boxes-Fusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"soft-nms-improving-object-detection-with-one","repo_url":"https://github.com/bharatsingh430/soft-nms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"soft-nms-improving-object-detection-with-one","repo_url":"https://github.com/fnando1995/INTEL_Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"soft-nms-improving-object-detection-with-one","repo_url":"https://github.com/jolibrain/caffe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"soft-nms-improving-object-detection-with-one","repo_url":"https://github.com/snilloO/obj_det_loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"soft-nms-improving-object-detection-with-one","repo_url":"https://github.com/snilloO/wheat_det","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"soft-nms-improving-object-detection-with-one","repo_url":"https://github.com/tkuanlun350/Kaggle_Ship_Detection_2018","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-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"position-sensitive-roi-pooling","method_name":"Position-Sensitive RoI Pooling"},{"method_slug":"r-fcn","method_name":"R-FCN"},{"method_slug":"soft-nms","method_name":"Soft-NMS"}],"datasets_introduced":[],"methods_introduced":[{"slug":"soft-nms","name":"Soft-NMS","full_name":"Soft-NMS"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.04503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.04503"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/snilloO/wheat_det","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/snilloO/obj_det_loss","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZFTurbo/Weighted-Boxes-Fusion","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jolibrain/caffe","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tkuanlun350/Kaggle_Ship_Detection_2018","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bharatsingh430/soft-nms","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fnando1995/INTEL_Project","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Iqbal1282/YoloV3","reach":{"status":"unanswered"}}],"summary":{"ran_fixture":3,"ran_honours":1},"by_repo_kind":{"listed":{"samples":4,"ran":4,"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":"c367359cfb501006","entry":"find_matching_box_fast","repo":"ZFTurbo/Weighted-Boxes-Fusion","repo_kind":"listed","path":"ensemble_boxes/ensemble_boxes_wbf.py","file_url":"https://github.com/ZFTurbo/Weighted-Boxes-Fusion/blob/HEAD/ensemble_boxes/ensemble_boxes_wbf.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c367359cfb501006"}},{"code_sha256_prefix":"7682de258c1c3404","entry":"gen_color_list","repo":"ZFTurbo/Weighted-Boxes-Fusion","repo_kind":"listed","path":"examples/example.py","file_url":"https://github.com/ZFTurbo/Weighted-Boxes-Fusion/blob/HEAD/examples/example.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7682de258c1c3404"}},{"code_sha256_prefix":"4495bc3c048b979e","entry":"get_weighted_box","repo":"ZFTurbo/Weighted-Boxes-Fusion","repo_kind":"listed","path":"ensemble_boxes/ensemble_boxes_wbf.py","file_url":"https://github.com/ZFTurbo/Weighted-Boxes-Fusion/blob/HEAD/ensemble_boxes/ensemble_boxes_wbf.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4495bc3c048b979e"}},{"code_sha256_prefix":"a7a36243e6ced0fc","entry":"prefilter_boxes","repo":"ZFTurbo/Weighted-Boxes-Fusion","repo_kind":"listed","path":"ensemble_boxes/ensemble_boxes_wbf.py","file_url":"https://github.com/ZFTurbo/Weighted-Boxes-Fusion/blob/HEAD/ensemble_boxes/ensemble_boxes_wbf.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a7a36243e6ced0fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}