{"url":"/method/adaptive-nms","slug":"adaptive-nms","name":"Adaptive NMS","full_name":"Adaptive NMS","full_name_withheld":false,"description_markdown":"**Adaptive Non-Maximum Suppression** is a non-maximum suppression algorithm that applies a dynamic suppression threshold to an instance according to the target density. The motivation is to find an NMS algorithm that works well for pedestrian detection in a crowd. Intuitively, a high NMS threshold keeps more crowded instances while a low NMS threshold wipes out more false positives. The adaptive-NMS thus applies a dynamic suppression strategy, where the threshold rises as instances gather and occlude each other and decays when instances appear separately. To this end, an auxiliary and learnable sub-network is designed to predict the adaptive NMS threshold for each instance.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Adaptive NMS: Refining Pedestrian Detection in a Crowd","paper":"/paper/adaptive-nms-refining-pedestrian-detection-in","first_author":"Songtao Liu","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/adaptive-nms-refining-pedestrian-detection-in"},"source":{"url":"http://arxiv.org/abs/1904.03629v1","title":"Adaptive NMS: Refining Pedestrian Detection in a Crowd","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":3,"archive_num_papers":3,"papers_newest_first":[{"paper":"/paper/g1020-a-benchmark-retinal-fundus-image","title":"G1020: A Benchmark Retinal Fundus Image Dataset for Computer-Aided Glaucoma Detection","date":"2020-05-28","arxiv_id":"2006.09158","n_code_links":3,"syntology":null},{"paper":"/paper/three-branch-and-mutil-scale-learning-for","title":"Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization","date":"2020-03-20","arxiv_id":"2003.09150","n_code_links":6,"syntology":null},{"paper":"/paper/adaptive-nms-refining-pedestrian-detection-in","title":"Adaptive NMS: Refining Pedestrian Detection in a Crowd","date":"2019-04-07","arxiv_id":"1904.03629","n_code_links":0,"syntology":null}],"papers_shown":3,"tasks":[{"task":"/task/fine-grained-image-classification","name":"Fine-Grained Image Classification","papers":1},{"task":"/task/fine-grained-image-recognition","name":"Fine-Grained Image Recognition","papers":1},{"task":"/task/fine-grained-visual-categorization","name":"Fine-Grained Visual Categorization","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/object-recognition","name":"Object Recognition","papers":1},{"task":"/task/optic-cup-segmentation","name":"Optic Cup Segmentation","papers":1},{"task":"/task/pedestrian-detection","name":"Pedestrian Detection","papers":1}],"tasks_shown":8,"n_tasks":8,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":2}],"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/adaptive-nms"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}