domainadaptation/salad

A toolbox for domain adaptation and semi-supervised learning. Contributions welcome.

43
/ 100
Emerging

This tool helps machine learning engineers and researchers compare and implement state-of-the-art domain adaptation techniques. It takes labeled data from a 'source' domain and unlabeled or differently distributed data from a 'target' domain, and outputs a more robust machine learning model that performs well across both. This is ideal for practitioners dealing with datasets that have shifted or changed over time, such as image or audio recognition tasks.

339 stars. No commits in the last 6 months.

Use this if you need to quickly benchmark different domain adaptation algorithms or integrate them into your deep learning experiments for tasks like image classification when your training data doesn't perfectly match your real-world deployment data.

Not ideal if you are looking for a simple, out-of-the-box solution without any coding, as this is a library for developers to build and evaluate models.

machine-learning-research deep-learning computer-vision data-drift model-generalization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

339

Forks

42

Language

HTML

License

MPL-2.0

Last pushed

May 15, 2021

Commits (30d)

0

Get this data via API

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

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