Haochen-Wang409/U2PL

[CVPR'22 & IJCV'24] Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels & Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation

44
/ 100
Emerging

This project helps computer vision engineers and researchers create more accurate pixel-level classifications for images, even when they have a limited amount of precisely labeled data. It takes in a mix of fully labeled images and many more unlabeled images. The output is a more robust image segmentation model that can accurately identify and delineate objects or regions within new images.

474 stars. No commits in the last 6 months.

Use this if you need to perform detailed object segmentation in images but face challenges with the high cost and time required for manual pixel-by-pixel labeling of large datasets.

Not ideal if your primary need is object detection (bounding boxes) or image classification (whole image labels) rather than fine-grained pixel segmentation.

image segmentation computer vision semi-supervised learning label efficiency AI model training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

474

Forks

59

Language

Python

License

Apache-2.0

Last pushed

Aug 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Haochen-Wang409/U2PL"

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