Doubly robust estimation of the unlabeled class distribution improves pseudo-labeling methods for realistic long-tailed semi-supervised learning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving realistic semi-supervised learning with doubly robust estimation
Doubly robust estimation of the unlabeled class distribution improves pseudo-labeling methods for realistic long-tailed semi-supervised learning.