AI Paper Atlas

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

CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection

Junhao Cai, Deyu Zeng, Junhao Pang, JunYu Chen, Qiwei Liang, Xiaopin ZHONG, Zongze Wu

ECCV 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 0 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 estimated (diffusion-normal) stream to real stream (ablation)CMDS-AD · MVTec 3D-AD 4-shotAUPRO@1%: 0.400 -> 0.410Improved
add estimated stream to real stream (ablation)CMDS-AD · MVTec 3D-AD 4-shotI-AUROC: 0.873 -> 0.871No clear effect
add real stream to estimated stream (ablation)CMDS-AD · MVTec 3D-AD 4-shotI-AUROC: 0.813 -> 0.871Improved
use Feature Mapper instead of standard MLP fusion (ablation)CMDS-AD · MVTec 3D-AD 4-shotAUPRO@1%: 0.399 -> 0.410Improved
use dual-stream architecture instead of MLP under identical diffusion priors (ablation)CMDS-AD · MVTec 3D-AD 4-shotPRO@1%: 39.9 -> 41.0Improved
use multiplicative fusion instead of additive fusion of anomaly maps (ablation)CMDS-AD · MVTec 3D-AD 4-shotAUPRO@1%: 0.401 -> 0.410Improved
use multiplicative fusion instead of additive fusion (ablation)CMDS-AD · MVTec 3D-AD 4-shotI-AUROC: 0.875 -> 0.871Mixed
fuse 2D and 3D maps by multiplication instead of 2D map only (ablation)CMDS-AD · MVTec 3D-AD 4-shotI-AUROC: 0.807 -> 0.871Improved
raise estimated-stream weight from 0.0 to 0.1 (ablation)CMDS-AD · EyeCandies 2-shotI-AUROC: 78.46% -> 80.20%Improved
raise estimated-stream weight from 0.0 to 0.1 (ablation)CMDS-AD · MVTec 3D-AD 4-shotAUPRO@30%: 95.63% -> 95.83%Improved
raise estimated-stream weight to 1.0 (ablation)CMDS-AD · EyeCandies 1-shotI-AUROC: 75.85%Hurt
vary synthetic samples N per real image from 1 to 3 (ablation)CMDS-AD · MVTec 3D-AD 4-shotPRO@1%: 40.4 (N=1), 40.6 (N=3) vs 41.0No clear effect

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