What is the role of entropy loss?
Hi, I am not able to understand the role of the entropy loss you use in your code, which was not mentioned in the paper.
https://github.com/lijin118/CGDM/blob/2d8fee0c8df158fb078ceed65979abbe46282506/utils.py#L429
Is this important to reproduce the result? Why is it not mentioned in the paper?
Hi, the entropy loss serves as a class balance regularization item which is inherited from MCD original paper and relative methods (please refer to the supplementary material of MCD). In addition, we mentioned this in the implementation details.
I am aware of the loss used on MCD paper, it is given as follows.
https://github.com/mil-tokyo/MCD_DA/blob/af10217c5c5451dcd8bc3e975a7d067c285cc029/visda_classification/res_train_main.py#L145
which seems to be different to the loss you used .
https://github.com/lijin118/CGDM/blob/2d8fee0c8df158fb078ceed65979abbe46282506/utils.py#L419
Can you explain the difference? Also, you additionally used an entropy minimization loss which is not used in MCD and also never mentioned in your paper.