Prediction-aware One-To-One, or POTO, is an assignment rule for object detection which dynamically assigns the foreground samples according to the quality of classification and regression simultaneously.
Source: End-to-End Object Detection with Fully Convolutional NetworkPaper | Code | Results | Date | Stars |
---|
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |