AI Paper Atlas

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

UniMMAD: Unified Multi-Modal and Multi-Class Anomaly Detection via MoE-Driven Feature Decompression

Yuan Zhao, Youwei Pang, Lihe Zhang, Hanqi Liu, Jiaming Zuo, Huchuan Lu, Xiaoqi Zhao

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 3 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
replace OCBE with the Feature Compression Module (ablation)RD-based baseline · Mean over 5 datasetsAUC_I: 75.624 -> 77.367Improved
add the general-to-specific paradigm with cross attention (ablation)baseline + FCM · Mean over 5 datasetsAUC_I: 77.367 -> 84.306Improved
add C-MoE decompression (ablation)general-to-specific model · Mean over 5 datasetsAUC_I: 84.306 -> 91.145Improved
use cross-condition routing instead of plain MoE (ablation)C-MoE · Mean over 5 datasetsAUC_I: 85.126 -> 91.145Improved
add routed experts (ablation)C-MoE · Mean over 5 datasetsAUC_I: 85.417 -> 91.145Improved
add multi-scale experts (ablation)C-MoE · Mean over 5 datasetsAUC_I: 88.900 -> 91.145Improved
add fixed expert (ablation)C-MoE · Mean over 5 datasetsAUC_I: 89.424 -> 91.145Improved
add multi-scale experts (ablation)C-MoE · MulSen-ADAUC_I: 81.960 -> 85.460Improved
use MoE-in-MoE instead of plain MoE (ablation)C-MoE · parameter efficiencyparameters: 75% fewerImproved
use UniMMAD instead of specialized CFMCFM · MVTec-3DAUC_I: 92.443 -> 92.527No clear effect
use UniMMAD instead of INP-Former in super multi-class settingINP-Former · VisAMF1_P: 44.4 -> 47.2Improved
use UniMMAD instead of INP-FormerINP-Former · MVTec-AD pixel-levelMF1_P: 60.7 -> 60.2Hurt

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