image

Semi-supervised learning by selective training with pseudo labels via confidence estimation

Publication Date:

Abstract

We propose a novel semi-supervised learning (SSL) method that adopts selective training with pseudo labels. In our method, we generate hard pseudo-labels and also estimate their confidence, which represents how likely each pseudo-label is to be correct... (read more)

Authors

Topics

https://openreview.net/pdf?id=hx0D7wn6qIy

0001-01-01 -