Viet-Anh on Software Logo

What is: FeatureNMS?

SourceFeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

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.