AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

DeMuS: Learning Decoupled Matching and Scoring for Batch Zero-Shot Industrial Anomaly Detection

Zhengyang Zhao, Hailong Sun, Binhang Qi, Hongrui Yu, Zhongchi Wang, Hang Xu

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 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
use DINOv3 backbone instead of CLIP (training-free) (ablation)mutual scoring · MVTec ADpixel AUROC / AUPRO: +2.88% pixel AUROC, +3.18% AUPROImproved
train only the matching adapter (no scoring adapter) (ablation)DeMuS · MVTec AD and VisA averageimage AUROC: 85.6 -> 82.6Hurt
add matching adapter to scoring-only variant (decoupling) (ablation)DeMuS · VisAimage AP: -2.49% drop in AP on VisA without itImproved
use multi-scale convolutional adapter instead of MLP bottleneck (ablation)DeMuS · MVTec ADimage AUROC: -4.91% drop on MVTec AD with MLPImproved
add MuSc-style multi-scale aggregation to MLP adapter (ablation)MLP adapter · MVTec AD and VisA averageimage AUROC: 89.2 -> 89.0No clear effect
use alignment-based correspondence oracle instead of average-pooled NN matching (ablation)DeMuS · MVTec AD and VisA averageimage AUROC: 89.5 -> 92.3Improved
add pose augmentation in training (ablation)DeMuS · MVTec AD and VisA averageimage AUROC: 89.9 -> 92.3Improved
add pose augmentation in training (ablation)DeMuS · MVTec AD (pose variation)image AUROC retention: -4.3% vs -3.0%Improved
add pose augmentation in training (ablation)DeMuS · VisA (pose variation)image AUROC retention: -14.7% vs -6.8%Improved
increase batch size from 2 to 4 (ablation)DeMuS · MVTec AD, VisA, Real-IAD averageimage AUROC: 92.28 at B=4; 24.27 ms per imageImproved
increase batch size beyond 4 (ablation)DeMuS · averageimage AUROC / latency: gains saturate while latency risesNo clear effect
increase top-k nearest neighbors from 1 to 5 (ablation)DeMuS · averageimage-level vs pixel-level: image 92.90 -> 93.30, pixel 95.11 -> 94.62Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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