← Back to all news
arXiv Machine Learning By Mame Diarra Toure, David A. Stephens

Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions

Read the original on arXiv Machine Learning →

arXiv:2602. 21160v3 Announce Type: replace-cross Abstract: In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI), that cannot distinguish whether a model's ignorance involves a benign or safety-critical class.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
1d ago

How Accurate Is Accurate Enough?

arXiv:2609.38785v1 Announce Type: new Abstract: How accurate must a numerical approximation be within a learning system? Primitive error alone cannot answer this question: errors of the same magnitud...

By Ningkang Peng, Qianfeng Yu, Jingyang Mao, Xiaoqian Peng, Yanhui Gu
More like this →
arXiv Computer Vision
Aug 27

Reliability analysis for BraTS-GoAT segmentation: a controlled robustness study of deep-ensemble uncertainty

The study evaluates the reliability of deep‑ensemble uncertainty for brain tumour segmentation on the BraTS‑GoAT dataset. A 5‑fold cross‑validated nnU‑Net baseline and a 3‑seed deep ensemble were compared for calibration and error detection; the ensemble showed modest gains in calibration on in‑distribution data but the single model’s confidence remained flat while accuracy degraded under synthetic corruptions. Disagreement among ensemble members rose sharply with corruption severity, proving to be a more sensitive indicator of acquisition shift than single‑model confidence.

By Riya Deepak Shet, Chenxi Liang, Le Zhang
computer-visionbenchmarks
More like this →