Non-maximum suppression is an integral part of the object detection pipeline. First, it sorts all detection boxes on the basis of their scores. The detection box $M$ with the maximum score is selected and all other detection boxes with a significant overlap (using a pre-defined threshold) with $M$ are suppressed. This process is recursively applied on the remaining boxes. As per the design of the algorithm, if an object lies within the predefined overlap threshold, it leads to a miss.
Soft-NMS solves this problem by decaying the detection scores of all other objects as a continuous function of their overlap with M. Hence, no object is eliminated in this process.
Source: Soft-NMS -- Improving Object Detection With One Line of CodePaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 19 | 33.93% |
Object | 15 | 26.79% |
Instance Segmentation | 3 | 5.36% |
Autonomous Driving | 2 | 3.57% |
regression | 2 | 3.57% |
Semantic Segmentation | 2 | 3.57% |
2D Object Detection | 1 | 1.79% |
Small Object Detection | 1 | 1.79% |
Object Tracking | 1 | 1.79% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |