nktoan/risk-distribution-matching

[WACV 2024] Domain Generalisation via Risk Distribution Matching

22
/ 100
Experimental

This project helps machine learning researchers evaluate and improve their models' ability to perform well on new, unseen datasets that differ from their training data. It takes in existing image classification benchmarks and outputs results showing how different models generalize across domains. This is for machine learning researchers working on robust model deployment.

No commits in the last 6 months.

Use this if you are a machine learning researcher aiming to improve your model's performance on diverse, previously unencountered real-world data distributions.

Not ideal if you are looking for a pre-trained, production-ready model or a tool for general image classification without a focus on domain generalization.

machine-learning-research domain-adaptation model-robustness computer-vision generalization-performance
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

23

Forks

Language

Python

License

Last pushed

Sep 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nktoan/risk-distribution-matching"

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