Birdwave Atlas.
Discover
OrganisationsProductsPeopleProjectsBeta
OpportunitiesEvents
Birdwave.
ImprintPrivacy PolicyTerms of UseCommunity RulesReport Illegal ContentContact

© 2026 Birdwave. Aachen, Germany. v0.1.4

Back to productsAnomaly Detection Model

PatchCore

Amazon Science

Community
Back to productsAnomaly Detection Model

PatchCore

Amazon Science

Community

Industrial anomaly-detection model that needs only good parts: memory bank of nominal patch features + nearest-neighbor matching reaches 99.1% image AUROC on MVTec AD — the reference method for cold-start visual defect detection.

Save it, compare it, request a quote or record that you have used it — with an account.

Sign in to save or compare
Updated39d ago

Tags

anomaly-detectionquality-inspectionfew-shotmvtec-adopen-source

Industrial anomaly-detection model that needs only good parts: memory bank of nominal patch features + nearest-neighbor matching reaches 99.1% image AUROC on MVTec AD — the reference method for cold-start visual defect detection.

licenseApache-2.0frameworkPyTorch

Input & output

Input

image

Output

Not specified

Industrial anomaly-detection model that needs only good parts: memory bank of nominal patch features + nearest-neighbor matching reaches 99.1% image AUROC on MVTec AD — the reference method for cold-start visual defect detection.

Save it, compare it, request a quote or record that you have used it — with an account.

Sign in to save or compare
Updated39d ago

Tags

anomaly-detectionquality-inspectionfew-shotmvtec-adopen-source

Overview

PatchCore (Roth et al., CVPR 2022, Amazon Science with University of Tübingen) detects and localizes visual defects using only defect-free training images. It stores locally-aware patch features from a pretrained backbone in a coreset-subsampled memory bank; at inference, patches far from their nearest nominal neighbor are flagged anomalous, yielding both an image-level score and a pixel-level anomaly map. It achieves up to 99.1% image-level AUROC on MVTec AD and stays strong in low-shot regimes (training from a handful of good images), while remaining CPU-deployable — properties that made it the default baseline for industrial QC. Reference code is Apache-2.0; a maintained implementation ships in Anomalib.

anomaly-detectionquality-inspectionfew-shotmvtec-adopen-source

Key features

  • Up to 99.1% image AUROC on MVTec AD
  • Trains on nominal images only — no defect labels
  • Strong low-shot performance for fast line changeover
  • Pixel-level anomaly maps localize the defect

This product is part of the Birdwave Atlas community.

Contribute evaluations, share integrations and help improve compatibility data.

Community feed

Discussions, evaluations, integrations and updates

At a glance

Method
feature matching
Input Type
image
Framework
PyTorch

Manufacturer

AS
Amazon Science
View organisation →

Developed by

  • AS
    Amazon ScienceLead
  • UO
    University of TübingenResearch lab

At a glance

Method
feature matching
Input Type
image
Framework
PyTorch

Manufacturer

AS
Amazon Science
View organisation →

Developed by

  • AS
    Amazon ScienceLead
  • UO
    University of TübingenResearch lab