arthurdouillard/CVPR2021_PLOP

Official code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation

43
/ 100
Emerging

This project helps computer vision engineers and researchers improve how machine learning models learn to identify different objects in images over time. It takes labeled image datasets and existing models, and outputs a refined model that can recognize new objects without forgetting previously learned ones. The primary users are those working on evolving computer vision systems, such as in robotics or autonomous driving.

156 stars. No commits in the last 6 months.

Use this if you need to continuously update a semantic segmentation model to recognize new categories of objects in images without degrading its performance on categories it already knows.

Not ideal if you are looking for a pre-trained, ready-to-use model for semantic segmentation without needing to train it on evolving datasets.

computer-vision semantic-segmentation continual-learning image-analysis machine-learning-operations
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

156

Forks

23

Language

Python

License

MIT

Last pushed

Feb 09, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/arthurdouillard/CVPR2021_PLOP"

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