peacelwh/VT-FSL

[NeurIPS 2025] VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning

32
/ 100
Emerging

This project helps researchers and machine learning engineers develop image classification systems even when they have very few labeled examples per category. It takes a small set of images and corresponding text descriptions as input, and outputs a highly accurate model for classifying new images into those categories. This is ideal for those working on tasks with limited data, like identifying rare species or niche product categories.

Use this if you need to build image classifiers with high accuracy but only have a handful of example images per class.

Not ideal if you have abundant labeled data for all your image categories or are primarily focused on text-only classification tasks.

image-classification few-shot-learning computer-vision machine-learning-research data-scarcity
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 4 / 25

How are scores calculated?

Stars

31

Forks

1

Language

Python

License

MIT

Last pushed

Dec 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/peacelwh/VT-FSL"

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