Proposal Filtering
DIoU-NMS
Introduced by Zheng et al. in Distance-IoU Loss: Faster and Better Learning for Bounding Box RegressionDIoU-NMS is a type of non-maximum suppression where we use Distance IoU rather than regular DIoU, in which the overlap area and the distance between two central points of bounding boxes are simultaneously considered when suppressing redundant boxes.
In original NMS, the IoU metric is used to suppress the redundant detection boxes, where the overlap area is the unique factor, often yielding false suppression for the cases with occlusion. With DIoU-NMS, we not only consider the overlap area but also central point distance between two boxes.
Source: Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 2 | 50.00% |
| BIG-bench Machine Learning | 1 | 25.00% |
| Real-Time Object Detection | 1 | 25.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
