Gradual Uncertainty Refinement via Noise-Driven Curriculum: A Post-Hoc Meta-Model for Robust Uncertainty Quantification

摘要

Reliable uncertainty quantification remains a major obstacle to the deployment of deep learning models under distributional shift. Existing post-hoc approaches that retrofit pretrained models either inherit misplaced confidence or merely reshape predictions, without advising the model when to be uncertain. We introduce GUIDE, a lightweight evidential learning meta-model that attaches to a frozen deep learning model and is explicitly guided on when and how to be uncertain. GUIDE identifies salient internal features via a calibration stage and then uses these features to construct a noise-driven curriculum that teaches the model when and how to express uncertainty. GUIDE requires no retraining, no architectural modifications, and no manual intermediate-layer selection to the base deep learning model, thus ensuring broad applicability and minimal user intervention. The resulting model avoids distilling overconfidence from the base model, improves out-of-distribution detection (≈ 77