'(Faster R-CNN) ROI Pooling layer is not differentiable w.r.t the box coordinates
The paper reports that "having an RoI pooling layer that is differentiable w.r.t the box coordinates is a nontrivial problem" and refers to "ROI Warping" (crops and resizes the features to a fixed shape) that makes it fully differentiable w.r.t the box coordinates.
I can't figure out why RoI pooling layer is not differentiable and ROI Warping is?
Solution 1:[1]
The inputs of RoI pooling are coordinates of reference boxes, and these coordinates are integer which are discrete, and the inputs of RoI pooling are also the outputs of Region Proposal Network, but the outputs of Region Proposal Network are continuous. So there exist a transformation between discrete input and continous output, this makes RoI cannot be differentiable.
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|---|
| Solution 1 | plll |