LAUSR

Trusted-Data-Guided Label Enhancement on Noisy Labels.

Sign Up to like & get
recommendations!
1 Published in 2022 at "IEEE transactions on neural networks and learning systems"

DOI: 10.1109/tnnls.2022.3162316

Abstract: Label distribution covers a certain number of labels, representing the degree to which each label describes the instance. Label enhancement (LE) is a procedure of recovering the label distribution from the logical labels in the… read more here.

Keywords: noise; trusted data; label distribution; label enhancement ... See more keywords