DIoU-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

Latest Papers

PAPER DATE
YOLOv4: Optimal Speed and Accuracy of Object Detection
| Alexey BochkovskiyChien-Yao WangHong-Yuan Mark Liao
2020-04-23
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
| Zhaohui ZhengPing WangWei LiuJinze LiRongguang YeDongwei Ren
2019-11-19

Tasks

TASK PAPERS SHARE
Object Detection 2 50.00%
adversarial training 1 25.00%
Real-Time Object Detection 1 25.00%

Components

COMPONENT TYPE
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories