statmlben/rankseg

RankSEG: A consistent ranking-based framework for segmentation

35
/ 100
Emerging

This project helps improve the accuracy of image segmentation in fields like medical imaging or autonomous driving. It takes the probability outputs from any existing trained segmentation neural network and processes them to produce more precise segmentation masks. This tool is for researchers or practitioners who need to extract distinct objects or regions from images with higher precision, such as analyzing cellular structures or identifying road boundaries.

Use this if you need to improve the Dice or IoU performance of your existing segmentation models without retraining them.

Not ideal if you are looking for a new segmentation model from scratch, as this module enhances existing models.

image-segmentation medical-imaging computer-vision autonomous-driving semantic-segmentation
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

30

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 30, 2025

Commits (30d)

0

Get this data via API

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

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