FeatureNMS

2000년 도입 · 논문 2편에서 사용

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.

출처: FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings

소개 논문: FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings