← Search

Jonas Unger

2 accepted papers

2026

Enhancing Out-of-Distribution Detection with Extended Logit Normalization

CVPR 2026

Out-of-distribution (OOD) detection is essential for the safe deployment of machine learning models. While extensive work has focused on designing effective scoring functions for OOD detection, relatively few studies explore training neural networks with calibration-oriented objectives, which often

Cited by 0SourcecodeScholar