ETN is a lightweight post-hoc module that applies a learned sample-dependent affine transformation to pretrained model logits and interprets the outputs as Dirichlet parameters to enable efficient uncertainty estimation.
Simple and principled uncertainty estimation with deterministic deep learning via distance awareness.Advances in neural informa- tion processing systems, 33:7498–7512
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation
ETN is a lightweight post-hoc module that applies a learned sample-dependent affine transformation to pretrained model logits and interprets the outputs as Dirichlet parameters to enable efficient uncertainty estimation.