Proposal Filtering
Soft-NMS
Introduced by Bodla et al. in Soft-NMS -- Improving Object Detection With One Line of CodeNon-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 Code
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 18 | 50.00% |
| Instance Segmentation | 3 | 8.33% |
| Autonomous Driving | 2 | 5.56% |
| Semantic Segmentation | 2 | 5.56% |
| Small Object Detection | 1 | 2.78% |
| Object Tracking | 1 | 2.78% |
| Visual Object Tracking | 1 | 2.78% |
| 3D Object Detection | 1 | 2.78% |
| Depth Estimation | 1 | 2.78% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
