A multi-expert distillation method with feature alignment and uncertainty weighting improves imbalanced grading on two medical datasets, but its state-of-the-art claim only holds for selected metrics in one scenario.
Nature medicine 28(1), 154–163 (2022)
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
-
Uncertainty-Aware Multi-Expert Knowledge Distillation for Imbalanced Disease Grading
A multi-expert distillation method with feature alignment and uncertainty weighting improves imbalanced grading on two medical datasets, but its state-of-the-art claim only holds for selected metrics in one scenario.