A semi-supervised method trains multiple divergent classifier heads and uses their prediction disagreements to identify and downweight out-of-distribution unlabeled samples.
Exploring simple siamese representation learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Diversify and Conquer: Open-set Disagreement for Robust Semi-supervised Learning with Outliers
A semi-supervised method trains multiple divergent classifier heads and uses their prediction disagreements to identify and downweight out-of-distribution unlabeled samples.