{"url":"/method/featurenms","slug":"featurenms","name":"FeatureNMS","full_name":"FeatureNMS","full_name_withheld":false,"description_markdown":"**Feature Non-Maximum Suppression**, or **FeatureNMS**, is a post-processing step for object detection models that removes duplicates where there are multiple detections outputted per object. FeatureNMS recognizes duplicates not only based on the intersection over union between the bounding boxes, but also based on the difference of feature vectors. These feature vectors can encode more information like visual appearance.","description_state":"present","introduced_year":null,"introduced_by":{"title":"FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings","paper":"/paper/featurenms-non-maximum-suppression-by","first_author":"Niels Ole Salscheider","n_authors":1,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/featurenms-non-maximum-suppression-by"},"source":{"url":"https://arxiv.org/abs/2002.07662v2","title":"FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings","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":2,"archive_num_papers":2,"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/featurenms-non-maximum-suppression-by","title":"FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings","date":"2020-02-18","arxiv_id":"2002.07662","n_code_links":1,"syntology":null}],"papers_shown":2,"tasks":[{"task":null,"name":"GPU","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":4,"n_tasks":4,"usage_by_year":[{"year":"2020","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/featurenms"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}