AI RESEARCH
When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
arXiv CS.LG
•
ArXi:2605.17795v1 Announce Type: new Learning with noisy labels (LNL) is typically benchmarked by closed-set classification accuracy, yet deployment often requires classifiers to reject out-of-distribution (OOD) inputs. We present a learner-agnostic ACC-OOD benchmark that freezes LNL checkpoints and evaluates them with standardized near-/far-OOD routing and post-hoc scores across synthetic and real label noise.