DDA-UQ models CLIP's embedding space with a Gaussian mixture and combines density and ambiguity evidence to predict failures, outperforming static UQ methods under distribution shifts.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning
DDA-UQ models CLIP's embedding space with a Gaussian mixture and combines density and ambiguity evidence to predict failures, outperforming static UQ methods under distribution shifts.