Question about the effect of ISDA on shallow layers of the network

blackfeather-wang / ISDA-for-Deep-Networks

An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.

582 stars 93 forks source link

Question about the effect of ISDA on shallow layers of the network #26

Open anonymousgit873 opened 3 years ago

anonymousgit873 commented 3 years ago

Hi, the ISDA is a nice work and very impressive.

I have a question about the effect of ISDA on shallow layers of the network. ISDA augments the deep features, which is the last conv layer of the network before FC. So it seems the augmented features are only used to train a robust FC layer. I'd like to know how ISDA will affect the training of previous conv layers.

Looking forward to your reply. Thanks!