mhamilton723/STEGO

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

51
/ 100
Established

This project helps you automatically identify and label different objects or regions within images, even if you don't have existing labels for what's in them. You provide a collection of images, and it outputs images where each pixel is assigned to a specific category, like 'sky,' 'car,' or 'road.' This is ideal for researchers, scientists, or analysts working with large image datasets where manual labeling is time-consuming or impractical.

785 stars. No commits in the last 6 months.

Use this if you need to automatically segment objects within images without the laborious and often impossible task of manually labeling every pixel in your dataset.

Not ideal if you already have perfectly labeled datasets or require pixel-perfect segmentation accuracy that only extensive human annotation can provide.

image-analysis remote-sensing medical-imaging environmental-monitoring object-detection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

785

Forks

159

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mhamilton723/STEGO"

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