tianyu0207/IGD

Official code for 'Deep One-Class Classification via Interpolated Gaussian Descriptor' [AAAI 2022 Oral]

35
/ 100
Emerging

This project helps identify unusual or defective items in a batch of images where most items are normal. You provide examples of what a 'normal' item looks like, and the system learns to spot deviations. This is useful for quality control inspectors or automated inspection systems in manufacturing.

Use this if you need to automatically detect anomalies or defects in visual data, such as products on an assembly line, without needing examples of what the defects look like.

Not ideal if you have detailed examples of all types of anomalies you want to detect, as more traditional supervised methods might be more suitable.

quality-control manufacturing-inspection defect-detection visual-anomaly-detection industrial-automation
No License No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

69

Forks

8

Language

Python

License

Last pushed

Oct 29, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tianyu0207/IGD"

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