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.
Source: Adaptive NMS: Refining Pedestrian Detection in a CrowdPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Fine-Grained Image Classification | 1 | 16.67% |
Fine-Grained Image Recognition | 1 | 16.67% |
Fine-Grained Visual Categorization | 1 | 16.67% |
Object Recognition | 1 | 16.67% |
Object Detection | 1 | 16.67% |
Pedestrian Detection | 1 | 16.67% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |