KaiyangZhou/ssdg-benchmark

Benchmarks for semi-supervised domain generalization.

39
/ 100
Emerging

This project helps machine learning researchers compare and evaluate different approaches for a challenging problem: training a model that performs well across various real-world scenarios, even when labeled data is scarce. It takes in image datasets with both limited labeled examples and abundant unlabeled data from multiple distinct environments. The output helps researchers understand which techniques create models that generalize best, providing a benchmark for semi-supervised domain generalization methods.

No commits in the last 6 months.

Use this if you are a machine learning researcher developing or evaluating methods to train robust models from limited labeled data that perform well across different visual domains.

Not ideal if you are looking for a pre-trained model or a tool to directly apply to a specific business problem without deep experimentation and research.

machine-learning-research domain-adaptation semi-supervised-learning computer-vision model-generalization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

72

Forks

10

Language

Python

License

MIT

Last pushed

Aug 25, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KaiyangZhou/ssdg-benchmark"

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