RADMI aggregates mutual information across decoder layers to proxy epistemic uncertainty in segmentation networks, showing the highest correlation with deep ensemble baselines among single-pass methods.
U-net: Convolutional networks for biomedical image segmentation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RADMI: Latent Information Aggregation as a Proxy for Model Uncertainty
RADMI aggregates mutual information across decoder layers to proxy epistemic uncertainty in segmentation networks, showing the highest correlation with deep ensemble baselines among single-pass methods.