Closed SirRob1997 closed 3 years ago
Hi, different convolutional layers should be able to locate discriminative spatial information consistently. The high-level convolutional layer tends to capture more semantic concepts while the low-level layer tends to capture more details. That's why spatial interpolation can be used in a convolutional network with average pooling.
I find myself confused about the naming conventions/comments and you should probably be more precise here. If I understood it correctly, the
channel_mean
is the mean used in Channel-Wise RSC and computes the mean across the spatial domain while thespatial_mean
is the mean used in Spatial-Wise RSC and computes the mean across the channel domain.This is why we need
F.interpolate
in the Spatial-Wise RSC since it doesn't make sense for architectures with average pooling afterwards like mentioned here: #3. By the way: This isn't mentioned in the paper, what is the intuition behind that even?