Skip to content

Reproducing the PatchCore anomaly detection algorithm from the paper "PatchCore: Anomaly Detection Without Training" using PyTorch. Features: WideResNet backbone, patch extraction, memory bank construction, coreset subsampling (Farthest Point Sampling), nearest-neighbor anomaly scoring, and ROC-AUC evaluation on MVTec AD.

Notifications You must be signed in to change notification settings

shiva2307/patchcore-anomaly-detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

patchcore-anomaly-detection

Reproducing the PatchCore anomaly detection algorithm from the paper "Towards Total Recall in Industrial Anomaly Detection". Features: WideResNet backbone, patch extraction, memory bank construction, coreset subsampling (Farthest Point Sampling), nearest-neighbor anomaly scoring, and ROC-AUC evaluation on MVTec AD.

About

Reproducing the PatchCore anomaly detection algorithm from the paper "PatchCore: Anomaly Detection Without Training" using PyTorch. Features: WideResNet backbone, patch extraction, memory bank construction, coreset subsampling (Farthest Point Sampling), nearest-neighbor anomaly scoring, and ROC-AUC evaluation on MVTec AD.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages