ysig/diff-mining

Diffusion Models as Data Mining Tools

35
/ 100
Emerging

This project helps researchers and analysts understand what specific visual elements in images are most representative or 'typical' for a given category. You provide a collection of labeled images (e.g., photos of different car models, types of scenes, or medical X-rays with conditions), and it identifies and groups the key visual patches that define each label. This allows image analysts, medical researchers, or urban planners to gain insights into distinguishing visual features.

No commits in the last 6 months.

Use this if you need to pinpoint and categorize the most characteristic visual components within a large dataset of images that belong to different labels.

Not ideal if you are looking to generate entirely new images, perform basic image classification, or if your dataset consists of non-visual data.

image-analysis medical-imaging visual-research pattern-recognition urban-studies
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

59

Forks

5

Language

Python

License

Last pushed

May 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ysig/diff-mining"

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