Methods › Computer Vision › Proposal Filtering › Adaptive NMS
Adaptive NMS
Introduced by Songtao Liu et al. in Adaptive NMS: Refining Pedestrian Detection in a Crowd
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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.
Papers archive 2025-07-28
3 shown of 3, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
G1020: A Benchmark Retinal Fundus Image Dataset for Computer-Aided Glaucoma Detection 28 May 2020 · 3 repositories · arXiv:2006.09158
-
Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization 20 Mar 2020 · 6 repositories · arXiv:2003.09150
-
Adaptive NMS: Refining Pedestrian Detection in a Crowd 7 Apr 2019 · 0 repositories · arXiv:1904.03629
Tasks archive 2025-07-28
8 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections