AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Defect Cue-Preserved Structural Feature Refinement for Few-Shot Anomaly Detection

Le Jiang, Yan Huang, Zhen Xu, Yong Xu, Hau-San Wong, Si Wu

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial 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 conditional anomaly cue amplification (CACA) (ablation)DCP-SFR · VisA 1-shotp-F1-max: 43.2 -> 44.6Improved
add CACA (ablation)DCP-SFR · VisA 1-shoti-AUROC: 91.5 -> 92.0Improved
add anomaly cue-guided localization (ACL) (ablation)DCP-SFR · VisA 1-shotp-AP: 37.7 -> 39.9Improved
add ACL (ablation)DCP-SFR · VisA 1-shoti-AUROC: 89.7 -> 92.0Improved
add structure-aware segmentation refinement (SSR) (ablation)DCP-SFR · VisA 1-shotp-AUROC: 97.1 -> 98.2Improved
add SSR (ablation)DCP-SFR · VisA 1-shotp-F1-max: 41.0 -> 44.6Improved
increase reference shots from 1 to 4DCP-SFR · VisAp-F1-max: 44.9 -> 47.1Improved
use DCP-SFR instead of AnomalyDINOfew-shot anomaly detection · MVTec AD 1-shotp-AP: 56.5 -> 61.2Improved
use DCP-SFR instead of AnomalyDINOfew-shot anomaly detection · VisA 1-shotp-F1-max: 45.1 -> 44.9Hurt

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