You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am confused about the spatial-wise RSC. If you apply average pooling to z (final feature map) and feed in the fully connected layer, I believe that for any channel of z, all values in that channel will be the same. Therefore, after an average pooling along channel dimension, all cells in the 7*7 weighting matrix will have the same value too. So, how do you select top p percentage? Did I miss something? Thank you.
The text was updated successfully, but these errors were encountered:
Hi, you are right. For alexnet, z is diretly used to guide muting. For resnet, downsampled middle layer spatial gradients are used to guide muting for z. Now I have seperated the code for alexnet and resnet respectively. Hope it helps.
Hi, you are right. For alexnet, z is diretly used to guide muting. For resnet, downsampled middle layer spatial gradients are used to guide muting for z. Now I have seperated the code for alexnet and resnet respectively. Hope it helps.
I am confused about the spatial-wise RSC. If you apply average pooling to z (final feature map) and feed in the fully connected layer, I believe that for any channel of z, all values in that channel will be the same. Therefore, after an average pooling along channel dimension, all cells in the 7*7 weighting matrix will have the same value too. So, how do you select top p percentage? Did I miss something? Thank you.
The text was updated successfully, but these errors were encountered: