FaPN
FaPN copied to clipboard
Codes about FeatureAlign_V2
In module FeatureAlign_v2
offset = self.offset(torch.cat([feat_arm, feat_up * 2], dim=1)) # concat for offset by compute the dif
Why multiple feat_up by 2?
We hope to enlarge the magnitude of upsampled features in case of suppression.
Thank you! I also have the same question!
thank reply!