Methods › Computer Vision › Proposal Filtering › FeatureNMS
FeatureNMS
Introduced by Niels Ole Salscheider in FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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.
Papers archive 2025-07-28
2 shown of 2, 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.
-
Work-Efficient Parallel Non-Maximum Suppression Kernels 1 Feb 2025 · 1 repository · arXiv:2502.00535
-
FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings 18 Feb 2020 · 1 repository · arXiv:2002.07662
Tasks archive 2025-07-28
4 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| GPU | 1 |
| Object | 1 |
| Object Detection | 1 |
| object-detection | 1 |
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