AI Paper Atlas

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

AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection

Zhaopeng Gu, Bingke Zhu, Guibo Zhu, Yingying Chen, Wei Ge, Ming Tang, Jinqiao Wang

AAAI 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 8 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
add component-level and global-level experts to patch-level experts (ablation)AnomalyMoE · MVTec LOCOimage-level AUC (%): 78.2 -> 87.5Improved
add component-level and global-level experts to patch-level experts (ablation)AnomalyMoE · MVTec-ADimage-level AUC (%): 98.2 -> 99.5Improved
add the third expert group to a two-group configuration (ablation)AnomalyMoE · MVTec LOCOimage-level AUC (%): 86.8 -> 87.5Improved
add Expert Selection Balancing (ESB) loss (ablation)AnomalyMoE · MVTec LOCOimage-level AUC (%): 84.2 -> 87.5Improved
add Expert Information Repulsion (EIR) loss (ablation)AnomalyMoE · MVTec LOCOimage-level AUC (%): 85.6 -> 87.5Improved
add ESB loss (ablation)AnomalyMoE · MVTec-ADimage-level AUC (%): 99.2 -> 99.5Improved
add EIR loss (ablation)AnomalyMoE · MVTec-ADimage-level AUC (%): 99.0 -> 99.5Improved
add ESB loss (ablation)AnomalyMoE · MVTec LOCOpixel-level AUC (%): 81.1 -> 82.2No clear effect
add EIR loss (ablation)AnomalyMoE · MVTec LOCOpixel-level AUC (%): 92.0 -> 82.2Hurt
use language-free experts instead of vision-language models (UniVAD)AnomalyMoE · Inference speedinference time (ms): 658.5 -> 58.5Improved
use AnomalyMoE instead of specialist reconstruction method DinomalyMVTec LOCO · MVTec LOCOimage-level AUC (%): 78.2 -> 87.5Improved
use AnomalyMoE instead of ReContrastRESC · RESCimage-level AUC (%): 94.6 -> 92.2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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