AI Paper Atlas

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

Distilling the Unknown to Unveil Certainty

Zhilin Zhao, Longbing Cao, Yixuan Zhang, Kun-Yu Lin, Wei‐Shi Zheng

TPAMI 2025 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 1 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
use CA- instead of best prior data-free method FeatureNormResNet101 · ImageNet-1K OODAverage AUROC: 85.57 -> 87.48Improved
use CA+ instead of LogitNormResNet101 · ImageNet-1K OODAverage AUROC: 86.15 -> 87.84Improved
use CA- instead of FeatureNormViT-L · ImageNet-1K OODAverage AUROC: 85.67 -> 87.44Improved
use CA+ instead of LogitNormViT-L · ImageNet-1K OODAverage AUROC: 86.04 -> 87.74Improved
use CA+ instead of ARPL on SSB-hard near-OODResNet101 · ImageNet-1K SSB-hardAUROC: 73.51 -> 69.63Hurt
use CA- instead of GEN on NINCO near-OODResNet101 · ImageNet-1K NINCOAUROC: 82.01 -> 82.80Improved

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