Closed jxhuang0508 closed 4 years ago
Yes, the interpretation in Tab1 is correct. Generally, entropy minimization is used for semi-supervised learning. However, it could also be used for unsupervised domain adaptation, when two domains are nearly aligned. In this case, you can think of the source data together with its labels as the labeled data in the semi-supervised setting. So in practice, to use entropy minimization properly, you may want to enable it after some alignment has been performed.
Understood, thanks for your reply!
Hi, thanks for sharing your work. However, I have some questions about your work.
Or you just introduce two types of self training ? entropy minimization and pseudo label retraining?
Thanks! looking forward to your reply!