Label Smoothing++ learns a class-wise non-target probability distribution to replace the uniform distribution in label smoothing, yielding accuracy gains across many benchmarks.
Generative alignment of pos- terior probabilities for source-free domain adaptation
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
-
Label Smoothing++: Enhanced Label Regularization for Training Neural Networks
Label Smoothing++ learns a class-wise non-target probability distribution to replace the uniform distribution in label smoothing, yielding accuracy gains across many benchmarks.