Anomaly Detection On Visa

Metrics

Detection AUROC

Results

Performance results of various models on this benchmark

Model Name	Detection AUROC	Paper Title	Repository
CFLOW	91.5	CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows
AnomalyDINO-S (full-shot)	97.6	AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2
WinCLIP+ (2-shot)	84.6	WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
Reverse Distillation	-	Anomaly Detection via Reverse Distillation from One-Class Embedding
GLASS	98.8	A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization
MuSc (zero-shot)	92.8	MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images
AnomalyCLIP	82.1	AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection
AnomalyDINO-S (4-shot)	92.6	AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2
APRIL-GAN	78.0	APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD
AST	94.9	Asymmetric Student-Teacher Networks for Industrial Anomaly Detection
SPD	87.8	SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation
STPM	83.3	Student-Teacher Feature Pyramid Matching for Anomaly Detection
SAA+	-	Segment Any Anomaly without Training via Hybrid Prompt Regularization
ReContrast	97.5	-	-
WinCLIP (0-shot)	78.1	WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
EfficientAD-S	97.5	EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies
PaDiM	-	PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization
AnoDDPM	78.2	AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise
SPADE	82.1	Sub-Image Anomaly Detection with Deep Pyramid Correspondences
DiffusionAD	98.8	DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection

0 of 47 row(s) selected.