AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Enhancing Out-of-Distribution Detection with Extended Logit Normalization

Yifan Ding, Xixi Liu, Jonas Unger, Gabriel Eilertsen

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train with ELogitNormMSP · CIFAR-100 far-OODAUROC: 77.76 -> 84.51Improved
train with ELogitNormReAct · CIFAR-100 far-OODAUROC: 80.39 -> 85.04Improved
train with ELogitNormGEN · CIFAR-100 far-OODAUROC: 79.68 -> 84.60Improved
train with ELogitNormfDBD · CIFAR-100 far-OODAUROC: 80.14 -> 85.40Improved
train with ELogitNormSCALE · CIFAR-100 far-OODAUROC: 81.42 -> 84.92Improved
train with ELogitNormKNN · CIFAR-100 far-OODAUROC: 82.40 -> 82.84Improved
train with ELogitNormMSP · CIFAR-100 near-OODAUROC: 80.27 -> 79.68Hurt
train with ELogitNormReAct · CIFAR-100 near-OODAUROC: 80.77 -> 78.04Hurt
train with ELogitNormSCALE · CIFAR-100 near-OODAUROC: 80.99 -> 78.86Hurt
train with ELogitNormKNN · ImageNet-200 far-OODAUROC: 93.16 -> 96.08Improved
train with ELogitNormMSP · ImageNet-200 far-OODAUROC: 90.13 -> 93.58Improved
train with ELogitNormfDBD · ImageNet-200 far-OODAUROC: 94.45 -> 94.45No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy