yfzhang114/AdaNPC

This is an official PyTorch implementation of the ICML 2023 paper AdaNPC and SIGKDD paper DRM.

35
/ 100
Emerging

This project helps machine learning researchers and practitioners evaluate and improve the performance of their image classification models when encountering new, unseen data variations. It takes pre-trained image classification models and various image datasets as input, then applies different test-time adaptation methods to assess how well the models generalize to out-of-distribution data. The output is a performance evaluation of these models, helping to identify robust solutions for real-world scenarios.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer working on computer vision and need to rigorously test how well your classification models perform on new, unexpected variations of data without retraining the entire model.

Not ideal if you are looking for a plug-and-play application for general image classification without needing to deeply understand or modify model adaptation techniques.

machine-learning-research computer-vision model-robustness domain-adaptation image-classification
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

86

Forks

7

Language

Python

License

MIT

Last pushed

Apr 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yfzhang114/AdaNPC"

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