shjo-april/RecurSeed_and_EdgePredictMix

[Under Review] RecurSeed and EdgePredictMix: Single-stage learning is sufficient for Weakly-Supervised Semantic Segmentation

33
/ 100
Emerging

This project helps computer vision researchers and practitioners efficiently perform weakly-supervised semantic segmentation. You provide images with basic image-level labels (e.g., 'this image contains a cat'), and the system automatically outputs pixel-level segmentation masks that accurately outline objects within those images. This is ideal for those needing to precisely identify objects in images without the tedious process of manual pixel-level annotation.

No commits in the last 6 months.

Use this if you need to create highly accurate segmentation masks for objects in images, but only have access to coarse, image-level labels for training.

Not ideal if you already have perfectly pixel-level annotated datasets, as its strength lies in improving segmentation from weaker supervision.

image-segmentation computer-vision object-detection machine-learning-research data-labeling
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

44

Forks

9

Language

Python

License

Last pushed

Jan 26, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/shjo-april/RecurSeed_and_EdgePredictMix"

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