ALR combines temporal-ensemble soft labels with an entropy regularizer to reduce overfitting to noisy labels, reporting accuracy gains over several baselines on CIFAR-10/100, ANIMAL-10N, Clothing1M, and WebVision.
, author Ding, Y
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Adaptive Label Refinement for Label Noise Learning
ALR combines temporal-ensemble soft labels with an entropy regularizer to reduce overfitting to noisy labels, reporting accuracy gains over several baselines on CIFAR-10/100, ANIMAL-10N, Clothing1M, and WebVision.