Gorilla-Lab-SCUT/TRIBE

[AAAI 2024] Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization

19
/ 100
Experimental

This project helps machine learning engineers and researchers improve the robustness of their image classification models when faced with real-world data shifts. It takes an existing image classification model and a stream of new, potentially corrupted or distribution-shifted images, then adapts the model to maintain high accuracy on this new data. The output is a more stable and accurate image classification model that can handle various types of real-world data streams.

No commits in the last 6 months.

Use this if you need to ensure your deployed image classification models remain accurate and reliable even when encountering corrupted, noisy, or class-imbalanced images in live environments.

Not ideal if you are developing new image classification models from scratch or need to handle non-image data types.

machine-learning-operations model-robustness image-classification data-drift computer-vision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

27

Forks

1

Language

Python

License

Last pushed

Apr 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Gorilla-Lab-SCUT/TRIBE"

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