nazmul-karim170/CNLL

[CVPR'22] Official Implementation of "CNLL: A Semi-supervised Approach for Continual Noisy Label Learning"

37
/ 100
Emerging

This project helps machine learning researchers evaluate and improve their image classification models. It takes an existing image dataset with potentially inaccurate labels and continuously trains the model while simultaneously identifying and correcting these noisy labels over time. The primary users are researchers or engineers working on robust computer vision systems.

No commits in the last 6 months.

Use this if you are a researcher or engineer developing image classification models and need a method to train effectively with noisy or evolving label data.

Not ideal if you are a practitioner looking for a ready-to-use image classification model or a general-purpose data cleaning tool outside of academic computer vision research.

image-classification machine-learning-research noisy-data-handling continual-learning computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

18

Forks

4

Language

Python

License

MIT

Last pushed

Oct 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nazmul-karim170/CNLL"

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