Anomaly Detection On Visa

评估指标

Detection AUROC

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
GLAD	99.5	GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection
DDAD	98.9	Anomaly Detection with Conditioned Denoising Diffusion Models
INP-Former ViT-B (model-unified multi-class)	98.9	Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection
Dinomaly ViT-L (model-unified multi-class)	98.9	Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection
GLASS	98.8	A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization
DiffusionAD	98.8	DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection
TransFusion	98.7	TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection
EfficientAD-M	98.1	EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies
HETMM	98.1	Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection
RealNet	97.8	RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection
PBAS	97.7	Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detection
AnomalyDINO-S (full-shot)	97.6	AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2
ReContrast	97.5	-	-
EfficientAD-S	97.5	EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies
FAIRnoDTD	97.1	FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection
URD	96.5	Unlocking the Potential of Reverse Distillation for Anomaly Detection
D3AD	96.0	Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection
AST	94.9	Asymmetric Student-Teacher Networks for Industrial Anomaly Detection
EdgRec	94.2	Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection
SuperSimpleNet	93.4	SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection

0 of 47 row(s) selected.