AI Paper Atlas

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

Hard-Normal Example-Aware Template Mutual Matching for Industrial Anomaly Detection

Zixuan Chen, Xiaohua Xie, Lingxiao Yang, Jianhuang Lai

IJCV 2024 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 12 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 backward matching to forward ATM (bidirectional ATMM) (ablation)F-ATM · MVTec AD (ALL templates)image AUROC: 99.2 -> 99.8Improved
add forward matching to backward ATM (ablation)B-ATM · MVTec AD (ALL templates)image AUROC: 99.0 -> 99.8Improved
use affine-invariant template matching instead of patch-level matching (ablation)Patch-level matching · MVTec AD (ALL templates)PRO: 94.9 -> 96.4Improved
use affine-invariant template matching instead of pixel-level matching (ablation)Pixel-level matching · MVTec AD (ALL templates)image AUROC: 96.6 -> 99.8Improved
combine forward and backward ATM (ablation)F-ATM · MVTec LOCOaverage image AUROC: 86.1 -> 88.1Improved
combine forward and backward ATM (logical anomalies) (ablation)F-ATM · MVTec LOCOlogical image AUROC: 78.8 -> 83.2Improved
combine forward and backward ATM (structural anomalies) (ablation)F-ATM · MVTec LOCOstructural image AUROC: 93.4 -> 92.9Hurt
use hard-normal-aware PTS_O instead of pixel cluster centres PC_O (ablation)ATMM · MVTec AD (60 sheets)image AUROC: 98.9 -> 99.5Improved
use PTS_K instead of pixel random selection (ablation)ATMM · MVTec AD (60 sheets)image AUROC: 98.4 -> 99.3Improved
use pixel-level instead of image-level selection (PC_K vs IC_K) (ablation)ATMM · MVTec AD (60 sheets)image AUROC: 97.1 -> 98.7Improved
compress template set to 60 sheets with PTSHETMM · MVTec AD (ALL templates)image AUROC: 99.8 -> 99.5Hurt
compress template set to 60 sheets with PTSHETMM · MVTec AD (ALL templates)inference speed (FPS): 4.7 FPS -> 26.1 FPSImproved

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