MedFormer-UR integrates evidential uncertainty from Dirichlet distributions and class-specific prototypes into a transformer to improve calibration and selective prediction on medical images across four modalities.
Enhanced multi-class brain tumor classification in mri using pre-trained cnns and transformer architectures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MedFormer-UR: Uncertainty-Routed Transformer for Medical Image Classification
MedFormer-UR integrates evidential uncertainty from Dirichlet distributions and class-specific prototypes into a transformer to improve calibration and selective prediction on medical images across four modalities.