ymxlzgy/FoundAD

[ICLR 2026] The implementation of the paper Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors

30
/ 100
Emerging

This tool helps quality control inspectors and manufacturing engineers quickly spot defects or anomalies in products. By providing just a few examples of normal products, it can identify unusual items in a batch. You input images of products, and it outputs highlighted images showing where the anomalies are located.

Use this if you need to automate visual inspection on a production line or in a lab, especially when you have very limited examples of defective items for training.

Not ideal if you require traditional machine learning models trained on large, pre-labeled datasets of both normal and anomalous items.

visual inspection quality control manufacturing defect detection industrial automation
No License No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 7 / 25
Community 6 / 25

How are scores calculated?

Stars

36

Forks

2

Language

Python

License

Last pushed

Mar 06, 2026

Commits (30d)

0

Get this data via API

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

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