peacelwh/VT-FSL
[NeurIPS 2025] VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning
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.
Stars
31
Forks
1
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
KimMeen/Time-LLM
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming...
om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
bytedance/SALMONN
SALMONN family: A suite of advanced multi-modal LLMs
NVlabs/OmniVinci
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
fixie-ai/ultravox
A fast multimodal LLM for real-time voice