CLUE trains networks with a loss that penalizes mismatch between predicted uncertainty and the model's loss, claiming better calibration across vision, regression, and language tasks.
Weight uncertainty in neural networks
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
-
CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignment
CLUE trains networks with a loss that penalizes mismatch between predicted uncertainty and the model's loss, claiming better calibration across vision, regression, and language tasks.