TaesikGong/NOTE

The official PyTorch Implementation of "NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation (NeurIPS '22)"

37
/ 100
Emerging

This project helps machine learning researchers evaluate their vision models when the real-world data streams they encounter are continuously changing. You input a pre-trained image classification model and a corrupted image dataset, and it outputs updated model performance metrics, showing how well the model adapts to new, unseen corruptions over time. It is designed for researchers or practitioners developing and assessing robust computer vision systems.

No commits in the last 6 months.

Use this if you need to rigorously test how well your image classification models adapt to evolving data conditions and corruptions in a continuous real-time scenario.

Not ideal if you are looking for a general-purpose image classification tool or a solution for static datasets without temporal shifts.

continual learning model robustness image classification data corruption computer vision research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

50

Forks

7

Language

Python

License

MIT

Last pushed

Dec 21, 2023

Commits (30d)

0

Get this data via API

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

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