如何在张量流中实现兴趣区域池化层？

Question

I am trying to create Faster RCNN like model. I get stuck when it comes to the ROI pooling from the feature map. I know here billinear sampling can be used but, it may not help for end to end training. How to implement this ROI pooling layer in tensorflow?

Answer 1

Bilinear sampling - as the name suggests - can actually be used even with end-to-end training as it's basically a linear operation. However, the disadvantage would be that your local maxima (ie strong excitations or certain units) could vanish because your sampling points just happen to be close to the minima. To remedy this, you can instead apply a max_pool(features, kernel, stride) operation where kernel and stride are adjusted such that the final output of this max pool operation does always have the same dimensions.

An example: your features have size 12x12 and you would like to pool to 4x4 , then setting kernel=(3,3) and stride=(3,3) would help you achieve that and for each 3x3 patch, the strongest excitations in the respective feature maps will be contained in the output.