statmlben/rankseg
RankSEG: A consistent ranking-based framework for segmentation
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.
Stars
30
Forks
2
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
MLSTRUCT/MLStructFP
Multi-unit floor plan dataset for architectural analysis and recognition
yassouali/pytorch-segmentation
:art: Semantic segmentation models, datasets and losses implemented in PyTorch.
wkentaro/pytorch-fcn
PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original...
meetps/pytorch-semseg
Semantic Segmentation Architectures Implemented in PyTorch
fregu856/deeplabv3
PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset.