how to use the regression loss to train the splitbrain？

[qyxqyx]

I am reimplementing the Split brain on my dataset, the my network is here: the path of ab->L:(input:84,84,2)->(42,42,16)->(21,21,32)->(21,21,32)->(11,11,64), and the feature(11,11,64) is average pooled across channel, get a (11,11,1)map, than, the loss is the L2 loss between the pooled feature map (11,11,1) and the downsampled L channel of the original image (11,11,1), the downsample operation is (84,84,1)->(11,11,1), I do not know whether my reimplementation is correct, please help me, thanks a lot!

[richzhang]

Thanks for trying to reimplement! The averaging across feature channels in the last layer seems potentially problematic. See Table 6 for the architecture here: https://arxiv.org/pdf/1611.09842.pdf . Thanks!