Datasets

Papers grouped by common anomaly detection datasets, with curated scores shown when available.

MVTec AD

Detection AUROC

#	Method	Paper	Conference
1	Memory Bank	SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling	CVPR-2026
2	Reconstruction-based	Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection	CVPR-2025
3	Few-shot	Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection	CVPR-2025
4	One-for-More	One-for-More: Continual Diffusion Model for Anomaly Detection	CVPR-2025
5	Unseen Visual Anomaly Generati	Unseen Visual Anomaly Generation	CVPR-2025
6	Zero-shot	AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios	CVPR-2025
7	DefectFill	DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection	CVPR-2025
8	Kaputt	Kaputt: A Large-Scale Dataset for Visual Defect Detection	ICCV-2025
9	CLIP	MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning	ICCV-2025
10	Toward Long-Tailed Online Anom	Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts	ICCV-2025
11	Towards Real Unsupervised Anom	Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learning	ICCV-2025
12	Adaptive Deviation Learning fo	Adaptive Deviation Learning for Visual Anomaly Detection with Data Contamination	WACV-2025
13	SPACE	SPACE: SPAtial-Aware Consistency rEgularization for Anomaly Detection in Industrial Applications	WACV-2025
14	Few-shot	AnomalyDINO: Boosting Patch-Based Few-Shot Anomaly Detection with DINOv2	WACV-2025
15	One-class	ROADS: Robust Prompt-Driven Multi-Class Anomaly Detection under Domain Shift	WACV-2025
16	ViT	Self-Supervised Anomaly Segmentation via Diffusion Models with Dynamic Transformer UNet	WACV-2025
17	Towards Accurate Unified Anoma	Towards Accurate Unified Anomaly Segmentation	WACV-2025

Curated scores are not available yet. Papers are currently ordered by citation count.

VisA

Detection AUROC

#	Method	Paper	Conference
1	Memory Bank	SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling	CVPR-2026
2	Reconstruction-based	Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection	CVPR-2025
3	Few-shot	Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection	CVPR-2025
4	One-for-More	One-for-More: Continual Diffusion Model for Anomaly Detection	CVPR-2025
5	Zero-shot	Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models	CVPR-2025
6	Unseen Visual Anomaly Generati	Unseen Visual Anomaly Generation	CVPR-2025
7	Kaputt	Kaputt: A Large-Scale Dataset for Visual Defect Detection	ICCV-2025
8	CLIP	MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning	ICCV-2025
9	Adaptive Deviation Learning fo	Adaptive Deviation Learning for Visual Anomaly Detection with Data Contamination	WACV-2025
10	SPACE	SPACE: SPAtial-Aware Consistency rEgularization for Anomaly Detection in Industrial Applications	WACV-2025
11	One-class	ROADS: Robust Prompt-Driven Multi-Class Anomaly Detection under Domain Shift	WACV-2025
12	Towards Accurate Unified Anoma	Towards Accurate Unified Anomaly Segmentation	WACV-2025

Curated scores are not available yet. Papers are currently ordered by citation count.

Real-IAD

Detection AUROC

#	Method	Paper	Conference
1	Real-IAD D3	Real-IAD D3: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detection	CVPR-2025
2	Reconstruction-based	Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection	CVPR-2025
3	Few-shot	Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection	CVPR-2025
4	CLIP	MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning	ICCV-2025

Curated scores are not available yet. Papers are currently ordered by citation count.

MVTec LOCO

Detection AUROC

#	Method	Paper	Conference
1	SPACE	SPACE: SPAtial-Aware Consistency rEgularization for Anomaly Detection in Industrial Applications	WACV-2025

Curated scores are not available yet. Papers are currently ordered by citation count.