{"doi":"10.1109/iccv.2017.593","title":"Soft-NMS — Improving Object Detection with One Line of Code","abstract":"Non-maximum suppression is an integral part of the object detection pipeline. First, it sorts all detection boxes on the basis of their scores. The detection box M with the maximum score is selected and all other detection boxes with a significant overlap (using a pre-defined threshold) with M are suppressed. This process is recursively applied on the remaining boxes. As per the design of the algorithm, if an object lies within the predefined overlap threshold, it leads to a miss. To this end, we propose Soft-NMS, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M. Hence, no object is eliminated in this process. Soft-NMS obtains consistent improvements for the coco-style mAP metric on standard datasets like PASCAL VOC 2007 (1.7% for both R-FCN and Faster-RCNN) and MS-COCO (1.3% for R-FCN and 1.1% for Faster-RCNN) by just changing the NMS algorithm without any additional hyper-parameters. Using Deformable-RFCN, Soft-NMS improves state-of-the-art in object detection from 39.8% to 40.9% with a single model. Further, the computational complexity of Soft-NMS is the same as traditional NMS and hence it can be efficiently implemented. Since Soft-NMS does not require any extra training and is simple to implement, it can be easily integrated into any object detection pipeline. Code for Soft-NMS is publicly available on GitHub (http://bit.ly/2nJLNMu).","journal":"2017 IEEE International Conference on Computer Vision (ICCV)","year":2017,"id":1736,"datarank":5.6047298802202254,"base_score":7.424165281042028,"endowment":7.424165281042028,"self_citation_contribution":1.1136247921563045,"citation_network_contribution":4.491105088063921,"self_endowment_contribution":1.1136247921563045,"citer_contribution":4.491105088063921,"corpus_percentile":81.2,"corpus_rank":2576,"citation_count":1675,"citer_count":95,"citers_with_citation_signal":77,"citers_with_endowment":77,"datacite_reuse_total":0,"is_dataset":false,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2017-10-01","authors":[{"id":19508,"name":"Bharat Singh","orcid":"0000-0003-4921-5996","position":1,"is_corresponding":false},{"id":19509,"name":"Rama Chellappa","orcid":"0000-0002-7638-1650","position":2,"is_corresponding":false},{"id":19510,"name":"Larry S. Davis","orcid":null,"position":3,"is_corresponding":false},{"id":19507,"name":"Navaneeth Bodla","orcid":null,"position":0,"is_corresponding":true}],"reference_count":31,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-03-01T18:20:47.508186Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}