Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Anomaly Detection On Btad

Metrics

Detection AUROC

Segmentation AUPRO

Results

Performance results of various models on this benchmark

Model Name	Detection AUROC	Segmentation AUPRO	Paper Title	Repository
ReConPatch WRN-50	95.8	97.5	ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection
PatchSVDD	-	-	Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation
CPR	94.8	85.1	Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval
MuSc (zero-shot)	96.16	83.43	MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images
RealNet	96.1	-	RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection
FastFlow+AltUB	-	-	AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection	-
PNI	-	-	PNI : Industrial Anomaly Detection using Position and Neighborhood Information
URD	93.9	78.5	Unlocking the Potential of Reverse Distillation for Anomaly Detection
AD-CLSCNFs	95.93	72.77	Anomaly Detection Using Normalizing Flow-Based Density Estimation and Synthetic Defect Classification
WeakREST-Un	94.4	84.9	Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers	-
VT-ADL	-	-	VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization
D3AD	95.2	83.2	Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection
Reverse Distillation ++	95.63	-	Revisiting Reverse Distillation for Anomaly Detection
PyramidFlow (Res18)	95.8	-	PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow

0 of 14 row(s) selected.