OSU-MLB/ViT_PEFT_Vision

[CVPR'25 (Highlight)] Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition

18
/ 100
Experimental

This project provides a comprehensive toolkit for researchers working with computer vision models, especially large pre-trained ones. It allows you to systematically evaluate and compare 16 different 'parameter-efficient fine-tuning' (PEFT) methods across various visual recognition tasks, data sizes, and domain differences. The primary users are vision AI researchers who need to consistently assess and reproduce the performance of different PEFT techniques.

No commits in the last 6 months.

Use this if you are a computer vision researcher needing to rigorously test and compare various parameter-efficient fine-tuning methods for large pre-trained models on different image datasets and scenarios.

Not ideal if you are an end-user simply looking to apply a pre-trained vision model without needing to research or compare different fine-tuning techniques yourself.

computer-vision-research model-fine-tuning AI-model-evaluation deep-learning-benchmarking image-recognition
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

46

Forks

Language

Jupyter Notebook

License

Last pushed

Jun 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OSU-MLB/ViT_PEFT_Vision"

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