Deformable RoI Pooling adds an offset to each bin position in the regular bin partition of the RoI Pooling. Similarly, the offsets are learned from the preceding feature maps and the RoIs, enabling adaptive part localization for objects with different shapes.
Source: Deformable Convolutional NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Action Detection | 2 | 12.50% |
Activity Detection | 2 | 12.50% |
Autonomous Driving | 2 | 12.50% |
Object Detection | 2 | 12.50% |
Semantic Segmentation | 2 | 12.50% |
Continual Learning | 1 | 6.25% |
Scene Understanding | 1 | 6.25% |
Activity Recognition | 1 | 6.25% |
Decision Making | 1 | 6.25% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |