AFN

AFN copied to clipboard

Question Regarding get_L2norm_loss_self_driven loss

4

Dear Yang, Thank you so much for sharing your code. I have a question regarding the proposed get_L2norm_loss_self_driven loss. In your code, for example in Office31, def get_L2norm_loss_self_driven(x): radius =...

JingWang18

Code for vanilla Office-Home

1

LiewFeng

Hi, I have a quick question toward get_L2norm_loss_self_driven in the example of Office 31. As you mentioned in #4, the loss value will only relate to delta r and it...

daddyke

Quenstion about get_L2norm_loss_self_drive

2

Hi there. I wonder why we should the L2 norm the feature 'x' first? The L2 norm of feature 'x' will always be 1, and the true norm of feature...

kevinbro96

Cannot reproduce the results on office31 and visda (vanilla)

2

Hi, the paper says you have used 10-crop during evaluation. But it didn't appear in the code. In addition, I cannot reproduce the results on both office31 and visda: 1)...

chester256