AIVResearch/MSANet

Official Pytorch implementation of Multi-Similarity and Attention Guidence for Boosting Few-Shot Segmentation.

36
/ 100
Emerging

This project helps researchers and engineers quickly segment new, unknown objects in images, even when very few examples are available for training. It takes in a few example images with their segmented objects (support images) and a new image (query image), then outputs the precise segmentation mask for the new object. This tool is for those working in computer vision or machine learning who need to perform accurate image segmentation with limited data.

No commits in the last 6 months.

Use this if you need to identify and outline novel objects in images, where only a handful of labeled examples are available for guidance.

Not ideal if you have a large dataset of pre-labeled images for every object class you want to segment, as more traditional methods might be simpler to implement.

image-segmentation computer-vision machine-learning-research object-detection sparse-data-learning
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

68

Forks

13

Language

Python

License

Last pushed

Jul 30, 2025

Commits (30d)

0

Get this data via API

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

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