realistic-ssl-evaluation icon indicating copy to clipboard operation
realistic-ssl-evaluation copied to clipboard

Published 20 hours ago • verified publisher icon brain-research

why this implementation of pseudo-labeling

Open hzhz2020 opened this issue 3 years ago • 0 comments

Hi I'm wondering in your implementation of pseudo-labeling, why did you use non-zero loss for unlabeled sample that has maximum predicted probability below the threshold.

hzhz2020 avatar Feb 24 '22 00:02 hzhz2020