AI Paper Atlas

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

Hunting Normality from Query Sample via Residual Learning for Generalist Anomaly Detection

Xiaolei Wang, Yuexin Wang, Tianhong Dai, Huihui Bai, Yao Zhao, Jimin Xiao

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection

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
add RFL alone (residual proxies directly hunt normality) to the NN baseline (ablation)HNQ · MVTec ADimage AUROC: 93.2 -> 90.4Hurt
add RFL alone to the NN baseline (ablation)HNQ · VisAimage AUROC: 82.3 -> 80.1Hurt
add NLS alone (initialized proxies) to the NN baseline (ablation)HNQ · MVTec ADimage AUROC: 93.2 -> 93.8Improved
add NLS alone to the NN baseline (ablation)HNQ · VisAimage AUROC: 82.3 -> 83.7Improved
combine RFL and NLS (residual guidance for normality learning) (ablation)HNQ · MVTec ADimage AUROC: 93.2 -> 96.0Improved
combine RFL and NLS (ablation)HNQ · VisAimage AUROC: 82.3 -> 87.3Improved
use residual R instead of mean support features as NLS value (ablation)HNQ NLS · MVTec ADimage AUROC: 96.0 -> 92.7Hurt
use mean support features instead of R as RFL key (ablation)HNQ RFL · MVTec ADimage AUROC: 96.0 -> 95.5Hurt
use mean support features instead of R as NLS key (remove residual guidance) (ablation)HNQ NLS · MVTec ADimage AUROC: 96.0 -> 94.4Hurt
learn normality proxies guided by residuals instead of modeling residual distribution (ResAD), 4-shotHNQ vs ResAD · BraTS (train on MVTec AD)image AUROC: 74.9 -> 85.4Improved
replace ResAD residual distribution fitting with two attention modulesHNQ vs ResAD · MVTec ADtraining time (hours): 20.6 -> 0.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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