invictus717/UniDG

Towards Unified and Effective Domain Generalization

34
/ 100
Emerging

This project offers a unified approach to improve the accuracy of existing artificial intelligence models when they encounter new, unfamiliar data. It takes your pre-trained vision models and enhances their performance on new, unseen image datasets without needing to retrain them extensively. This is useful for AI practitioners and researchers who deploy models in real-world scenarios where data characteristics can shift.

No commits in the last 6 months.

Use this if your image recognition or classification models perform well on your training data but struggle with accuracy when deployed to new environments or on datasets with different characteristics.

Not ideal if you are looking for a completely new model architecture rather than an improvement method for existing ones, or if your primary concern is reducing initial model training time.

AI model deployment image recognition computer vision unseen data performance model adaptation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

32

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Nov 27, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/invictus717/UniDG"

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