Seokju-Cho/Volumetric-Aggregation-Transformer

Official Implementation of VAT

39
/ 100
Emerging

This project helps computer vision researchers and practitioners automatically identify and outline specific objects or regions within images, even when very few examples are available. You provide a few example images with the target object highlighted, and it outputs segmented images where the object of interest is precisely separated from the background. This tool is ideal for those working on advanced image analysis, such as in medical imaging or autonomous driving.

159 stars. No commits in the last 6 months.

Use this if you need to precisely segment objects in images, particularly when you have limited labeled data for training your segmentation model.

Not ideal if you are looking for a general-purpose object detection tool or if you have abundant labeled data for standard supervised segmentation.

image-segmentation computer-vision few-shot-learning object-detection image-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

159

Forks

16

Language

Python

License

MIT

Last pushed

Jan 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Seokju-Cho/Volumetric-Aggregation-Transformer"

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