{"url":"/method/soft-nms","slug":"soft-nms","name":"Soft-NMS","full_name":"Soft-NMS","full_name_withheld":false,"description_markdown":"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)\r\nwith $M$ 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. \r\n\r\n**Soft-NMS** solves this problem by decaying the detection scores of all other objects as a continuous function of their overlap with M. Hence, no object is eliminated in this process.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Soft-NMS -- Improving Object Detection With One Line of Code","paper":"/paper/soft-nms-improving-object-detection-with-one","first_author":"Navaneeth Bodla","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/soft-nms-improving-object-detection-with-one"},"source":{"url":"http://arxiv.org/abs/1704.04503v2","title":"Soft-NMS -- Improving Object Detection With One Line of Code","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Proposal Filtering","url":"/methods/category/proposal-filtering","pwc_aliases":[]}],"n_papers_tagged":22,"archive_num_papers":22,"papers_newest_first":[{"paper":"/paper/work-efficient-parallel-non-maximum","title":"Work-Efficient Parallel Non-Maximum Suppression Kernels","date":"2025-02-01","arxiv_id":"2502.00535","n_code_links":1,"syntology":null},{"paper":"/paper/underwater-soft-coral-detection-scoralnet-for","title":"Underwater Soft Coral Detection: SCoralNet for Accurate and Efficient Annotation.","date":"2024-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-approaches-to-building-rooftop","title":"Deep learning approaches to building rooftop thermal bridge detection from aerial images","date":"2022-12-12","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Detection Selection Algorithm: A Likelihood based Optimization Method to Perform Post Processing for Object Detection","date":"2022-12-12","arxiv_id":"2212.05706","n_code_links":0,"syntology":null},{"paper":null,"title":"An advanced YOLOv3 method for small object detection","date":"2022-12-06","arxiv_id":"2212.02809","n_code_links":0,"syntology":null},{"paper":"/paper/neighbortrack-improving-single-object","title":"NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets","date":"2022-11-12","arxiv_id":"2211.06663","n_code_links":1,"syntology":null},{"paper":null,"title":"MDS-Net: A Multi-scale Depth Stratification Based Monocular 3D Object Detection Algorithm","date":"2022-01-12","arxiv_id":"2201.04341","n_code_links":0,"syntology":null},{"paper":null,"title":"DRPN: Making CNN Dynamically Handle Scale Variation","date":"2021-12-21","arxiv_id":"2112.10963","n_code_links":0,"syntology":null},{"paper":"/paper/confidence-propagation-cluster-unleash-full","title":"Confidence Propagation Cluster: Unleash Full Potential of Object Detectors","date":"2021-12-01","arxiv_id":"2112.00342","n_code_links":1,"syntology":null},{"paper":null,"title":"Quantum-soft QUBO Suppression for Accurate Object Detection","date":"2020-07-28","arxiv_id":"2007.13992","n_code_links":0,"syntology":null},{"paper":"/paper/houghnet-integrating-near-and-long-range","title":"HoughNet: Integrating near and long-range evidence for bottom-up object detection","date":"2020-07-05","arxiv_id":"2007.02355","n_code_links":2,"syntology":null},{"paper":"/paper/dynamic-r-cnn-towards-high-quality-object","title":"Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training","date":"2020-04-13","arxiv_id":"2004.06002","n_code_links":3,"syntology":{"ran":2,"of":18,"unverified":16,"pointer_only":0}},{"paper":"/paper/1st-place-solutions-for-openimage2019-object","title":"1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation","date":"2020-03-17","arxiv_id":"2003.07557","n_code_links":2,"syntology":null},{"paper":"/paper/matrixnets-a-new-scale-and-aspect-ratio-aware","title":"MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection","date":"2020-01-09","arxiv_id":"2001.03194","n_code_links":1,"syntology":null},{"paper":"/paper/190408900","title":"CornerNet-Lite: Efficient Keypoint Based Object Detection","date":"2019-04-18","arxiv_id":"1904.08900","n_code_links":6,"syntology":{"ran":1,"of":27,"unverified":26,"pointer_only":0}},{"paper":"/paper/centernet-object-detection-with-keypoint","title":"CenterNet: Keypoint Triplets for Object Detection","date":"2019-04-17","arxiv_id":"1904.08189","n_code_links":20,"syntology":{"ran":2,"of":11,"unverified":9,"pointer_only":2}},{"paper":"/paper/thundernet-towards-real-time-generic-object","title":"ThunderNet: Towards Real-time Generic Object Detection","date":"2019-03-28","arxiv_id":"1903.11752","n_code_links":3,"syntology":null},{"paper":"/paper/bottom-up-object-detection-by-grouping","title":"Bottom-up Object Detection by Grouping Extreme and Center Points","date":"2019-01-23","arxiv_id":"1901.08043","n_code_links":2,"syntology":{"ran":1,"of":5,"unverified":4,"pointer_only":0}},{"paper":"/paper/hybrid-task-cascade-for-instance-segmentation","title":"Hybrid Task Cascade for Instance Segmentation","date":"2019-01-22","arxiv_id":"1901.07518","n_code_links":5,"syntology":{"ran":0,"of":11,"unverified":11,"pointer_only":0}},{"paper":"/paper/scale-aware-trident-networks-for-object","title":"Scale-Aware Trident Networks for Object Detection","date":"2019-01-07","arxiv_id":"1901.01892","n_code_links":4,"syntology":null},{"paper":"/paper/an-analysis-of-scale-invariance-in-object-1","title":"An Analysis of Scale Invariance in Object Detection - SNIP","date":"2017-11-22","arxiv_id":"1711.08189","n_code_links":0,"syntology":null},{"paper":"/paper/soft-nms-improving-object-detection-with-one","title":"Soft-NMS -- Improving Object Detection With One Line of Code","date":"2017-04-14","arxiv_id":"1704.04503","n_code_links":8,"syntology":{"ran":4,"of":4,"unverified":0,"pointer_only":0}}],"papers_shown":22,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":19},{"task":"/task/object-detection-1","name":"object-detection","papers":18},{"task":"/task/object","name":"Object","papers":15},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":3},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":2},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/regression-1","name":"regression","papers":2},{"task":"/task/2d-object-detection","name":"2D Object Detection","papers":1},{"task":"/task/3d-object-detection","name":"3D Object Detection","papers":1},{"task":"/task/depth-estimation","name":"Depth Estimation","papers":1},{"task":"/task/depth-prediction","name":"Depth Prediction","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/image-generation","name":"Image Generation","papers":1},{"task":"/task/keypoint-estimation","name":"Keypoint Estimation","papers":1},{"task":"/task/monocular-3d-object-detection","name":"Monocular 3D Object Detection","papers":1},{"task":"/task/object-tracking","name":"Object Tracking","papers":1},{"task":"/task/open-question","name":"Open-Ended Question Answering","papers":1},{"task":"/task/pedestrian-detection","name":"Pedestrian Detection","papers":1}],"tasks_shown":20,"n_tasks":27,"usage_by_year":[{"year":"2017","papers":2},{"year":"2019","papers":6},{"year":"2020","papers":5},{"year":"2021","papers":2},{"year":"2022","papers":5},{"year":"2024","papers":1},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/soft-nms"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}