A continual-learning plugin that identifies low-density feature samples as noisy-label errors and erases them by fine-tuning a pseudo-class neuron, improving accuracy and reducing forgetting in most tested settings.
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
-
ErrorEraser: Unlearning Data Bias for Improved Continual Learning
A continual-learning plugin that identifies low-density feature samples as noisy-label errors and erases them by fine-tuning a pseudo-class neuron, improving accuracy and reducing forgetting in most tested settings.