semisup-semseg icon indicating copy to clipboard operation
semisup-semseg copied to clipboard

Published 20 hours ago • verified publisher icon sud0301

About cosine_loss in MLMT

Open HHuiwen opened this issue 3 years ago • 0 comments

Hi authors, Thank you very much for sharing the code! In the paper, consistency loss is used for all available samples, but Why you only compute unlabeled data in the code? Is there any wrong with train_mlmt.py?

image

image

HHuiwen avatar May 03 '21 08:05 HHuiwen