yasserben/CLOUDS

[CVPR 2024] Official Implementation of Collaborating Foundation models for Domain Generalized Semantic Segmentation

29
/ 100
Experimental

This project helps computer vision researchers and practitioners build robust image segmentation models that work well in new, previously unseen environments. It takes a labeled dataset from a "source domain" (e.g., images from a specific city or weather condition) and trains a model that can accurately segment objects in images from entirely different, unlabeled "target domains" (e.g., different cities, varying weather). This is ideal for those needing to deploy vision systems in diverse, unpredictable real-world settings.

No commits in the last 6 months.

Use this if you need an image segmentation model trained on one type of data to perform accurately across many different, unencountered visual conditions.

Not ideal if your image segmentation tasks always occur within highly controlled, consistent visual environments.

computer-vision image-segmentation domain-generalization autonomous-systems robotics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

76

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Apr 04, 2025

Commits (30d)

0

Get this data via API

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

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