HKUST-LongGroup/Diff-II

[CVPR 2025] PyTorch implementation of Diff-II

22
/ 100
Experimental

When you have too few images to properly train an image classifier, Diff-II helps by creating new, high-quality synthetic images. It takes your existing small dataset of images and generates additional, diverse examples, which you can then use to train more accurate image classification models. This is for researchers, data scientists, or machine learning practitioners working with limited image data.

No commits in the last 6 months.

Use this if you need to improve the performance of an image classification model but are constrained by a small number of training images for specific categories.

Not ideal if you already have a very large and diverse dataset for your image classification tasks, as its primary benefit is in data-scarce scenarios.

image-classification data-augmentation machine-learning-research computer-vision limited-data-training
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

25

Forks

2

Language

Python

License

Last pushed

Feb 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/HKUST-LongGroup/Diff-II"

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