DAMEL reduces both prediction bias and variance in class-imbalanced learning by concatenating multi-expert representations with an auxiliary balanced classifier and aggregating model weights across training epochs.
Class-balanced distil- lation for long-tailed visual recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learning
DAMEL reduces both prediction bias and variance in class-imbalanced learning by concatenating multi-expert representations with an auxiliary balanced classifier and aggregating model weights across training epochs.