thuml/Transfer-Learning-Library

Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization

49
/ 100
Emerging

When you have a well-performing AI model trained on specific data (like images from one type of camera) but need it to work equally well on similar data from a different source (like another camera type or dataset), this library helps bridge that gap. It takes your existing model and new, slightly different data, and adapts the model so it performs robustly across both. This is ideal for AI researchers and machine learning engineers dealing with real-world data variability.

3,884 stars. No commits in the last 6 months.

Use this if your AI model's performance drops when applied to data that is similar but not identical to its training data, and you want to adapt it without retraining from scratch.

Not ideal if you are looking for a no-code solution or a tool for general machine learning tasks that don't involve adapting models across different data domains.

AI model adaptation image classification object detection semantic segmentation robust AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

3,884

Forks

591

Language

Python

License

MIT

Last pushed

May 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thuml/Transfer-Learning-Library"

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