HyperAI超神经

Anomaly Detection On Aebad S

评估指标

Detection AUROC

Segmentation AUPRO

评测结果

各个模型在此基准测试上的表现结果

			Paper Title
MSFR	87.1	90.4	Multi-scale feature reconstruction network for industrial anomaly detection
MMR	84.7	89.1	Industrial Anomaly Detection with Domain Shift: A Real-world Dataset and Masked Multi-scale Reconstruction
ReverseDistillation	81.0	85.6	Anomaly Detection via Reverse Distillation from One-Class Embedding
PatchCore	71.0	87.8	Towards Total Recall in Industrial Anomaly Detection
DRAEM	62.5	63.6	DRAEM - A Discriminatively Trained Reconstruction Embedding for Surface Anomaly Detection
NSA	56.7	45.9	Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization
InTra	44.2	74.7	Inpainting Transformer for Anomaly Detection
RIAD	40.0	58.2	Reconstruction by Inpainting for Visual Anomaly Detection

0 of 8 row(s) selected.

HyperAI超神经

Anomaly Detection On Aebad S

评估指标

Detection AUROC

Segmentation AUPRO

评测结果

各个模型在此基准测试上的表现结果

			Paper Title
MSFR	87.1	90.4	Multi-scale feature reconstruction network for industrial anomaly detection
MMR	84.7	89.1	Industrial Anomaly Detection with Domain Shift: A Real-world Dataset and Masked Multi-scale Reconstruction
ReverseDistillation	81.0	85.6	Anomaly Detection via Reverse Distillation from One-Class Embedding
PatchCore	71.0	87.8	Towards Total Recall in Industrial Anomaly Detection
DRAEM	62.5	63.6	DRAEM - A Discriminatively Trained Reconstruction Embedding for Surface Anomaly Detection
NSA	56.7	45.9	Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization
InTra	44.2	74.7	Inpainting Transformer for Anomaly Detection
RIAD	40.0	58.2	Reconstruction by Inpainting for Visual Anomaly Detection

0 of 8 row(s) selected.

Anomaly Detection On Aebad S | SOTA | HyperAI超神经