LilitYolyan/CutPaste

Unofficial implementation of Google "CutPaste: Self-Supervised Learning for Anomaly Detection and Localization" in PyTorch

46
/ 100
Emerging

This project helps quality control engineers and manufacturing line managers automate visual inspection. You provide images of your product, and it learns what a 'normal' product looks like. It then identifies new, unseen products that have defects or anomalies, improving inspection efficiency and consistency.

130 stars. No commits in the last 6 months.

Use this if you need to detect unusual patterns or defects in images of manufactured goods without having a large dataset of already-identified anomalies.

Not ideal if you already have a comprehensive dataset of both normal and defective items with clear labels for supervised learning.

quality-control manufacturing-inspection defect-detection visual-inspection anomaly-detection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

130

Forks

29

Language

Python

License

MIT

Last pushed

Apr 21, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LilitYolyan/CutPaste"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.