hynnsk/PPAP

This is the official pytorch implementation of "Progressive Proxy Anchor Propagation for Unsupervised Semantic Segmentation" (ECCV 2024).

22
/ 100
Experimental

This project helps machine learning engineers and researchers automatically categorize pixels in images without needing manually labeled training data. You provide raw image datasets, and the system processes them to output segmented images where each pixel is assigned to a semantic category (like 'sky', 'road', or 'person'). This is ideal for those working on computer vision applications who need to segment large volumes of images but lack the resources for extensive manual annotation.

No commits in the last 6 months.

Use this if you need to perform semantic segmentation on images but want to avoid the time-consuming and labor-intensive process of manual image labeling.

Not ideal if you require segmentation based on highly specific or rare categories that are not well-represented by pre-trained models or if you need pixel-perfect accuracy for safety-critical applications.

computer-vision image-segmentation unsupervised-learning object-recognition image-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

18

Forks

Language

Python

License

MIT

Last pushed

Aug 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/hynnsk/PPAP"

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