Jiahao000/MosaicFusion

[IJCV 2024] MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation

31
/ 100
Emerging

MosaicFusion helps computer vision specialists create diverse training datasets for image analysis, especially for identifying unusual or rare objects. It takes a list of object categories and generates synthetic images with precise outlines of those objects. This tool is for professionals building and improving image segmentation models, such as those used in autonomous driving, medical imaging, or retail analytics.

128 stars. No commits in the last 6 months.

Use this if you need to expand your training data for object detection and segmentation models, particularly when you lack real-world examples for certain categories.

Not ideal if you're looking for a complete, end-to-end solution for training and deploying an image segmentation model without any programming knowledge.

computer-vision image-segmentation data-augmentation object-detection machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

128

Forks

3

Language

Python

License

Last pushed

Oct 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Jiahao000/MosaicFusion"

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