AI Paper Atlas

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

Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection

Xincheng Yao, Ruoqi Li, Zefeng Qian, Yan Luo, Chongyang Zhang

ICCV 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 42 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 entropy constraint to the intra-correlation branch (ablation)FOD intra-correlation · MVTecAD, BTAD, MVTec3D-RGB averageimage-level AUROC: 0.740 -> 0.817Improved
combine reconstruction and KL divergence scoring instead of divergence alone (intra branch) (ablation)FOD intra-correlation · average over three datasetsimage-level AUROC: 0.817 -> 0.915Improved
use mean features instead of coreset features as external reference (ablation)FOD inter-correlation · average over three datasetsimage-level AUROC: 0.836 -> 0.923Improved
add intra- and inter-correlation to patch-wise reconstruction Transformer (ablation)FOD · average over three datasetsimage-level AUROC: 0.905 -> 0.945Improved
add intra-correlation view to patch-wise reconstruction on MVTecAD (ablation)FOD · MVTecADimage-level AUROC: 0.972 -> 0.974No clear effect
add reconstruction to correlation-only scoring (Intra+Inter) (ablation)FOD · average over three datasetsimage-level AUROC: 0.877 -> 0.945Improved
FOD versus PatchCore using the same backboneFOD · MVTecADimage-level AUROC: 0.983 -> 0.992Improved
FOD versus best competitor CFLOW on harder MVTec3D-RGBFOD · MVTec3D-RGBimage-level AUROC: 0.851 -> 0.884Improved
FOD versus CFLOW and PatchCore on anomaly localizationFOD · BTAD pixel-levelpixel-level AUROC: 0.978 -> 0.975No 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