PIoU Loss is a loss function for oriented object detection which is formulated to exploit both the angle and IoU for accurate oriented bounding box regression. The PIoU loss is derived from IoU metric with a pixel-wise form.
Source: PIoU Loss: Towards Accurate Oriented Object Detection in Complex EnvironmentsPaper | Code | Results | Date | Stars |
---|
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |