Non Maximum Suppression is a computer vision method that selects a single entity out of many overlapping entities (for example bounding boxes in object detection). The criteria is usually discarding entities that are below a given probability bound. With remaining entities we repeatedly pick the entity with the highest probability, output that as the prediction, and discard any remaining box where a $\text{IoU} \geq 0.5$ with the box output in the previous step.
Image Credit: Martin Kersner
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 183 | 31.94% |
Semantic Segmentation | 24 | 4.19% |
Real-Time Object Detection | 19 | 3.32% |
Instance Segmentation | 19 | 3.32% |
Pedestrian Detection | 14 | 2.44% |
Image Classification | 11 | 1.92% |
General Classification | 11 | 1.92% |
Classification | 10 | 1.75% |
Pose Estimation | 8 | 1.40% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |