SNGP models match deterministic neural network accuracy on biomedical images while providing superior uncertainty calibration and OOD rejection across six datasets.
Across multiple datasets, it maintains strong calibration and in- distribution accuracy while substantially improving OOD detection over deterministic and Monte Carlo methods
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Uncertainty-Aware Image Classification In Biomedical Imaging Using Spectral-normalized Neural Gaussian Processes
SNGP models match deterministic neural network accuracy on biomedical images while providing superior uncertainty calibration and OOD rejection across six datasets.