katelyn98/CorruptionRobustness

We investigated corruption robustness across different architectures including Convolutional Neural Networks, Vision Transformers, and the MLP-Mixer.

23
/ 100
Experimental

This project investigates how well different image recognition models, like Convolutional Neural Networks and Vision Transformers, perform when images are corrupted with noise or distortions. It takes various pre-trained image classification models as input and evaluates their resilience to common image corruptions. Machine learning researchers and practitioners working on robust computer vision systems would find this useful.

No commits in the last 6 months.

Use this if you are developing or evaluating image recognition systems and need to understand their reliability under real-world, imperfect conditions.

Not ideal if you are looking for a tool to apply image corruptions or train models, as this project focuses on analysis rather than practical application.

computer-vision-research deep-learning-robustness image-classification model-evaluation visual-AI-development
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

16

Forks

2

Language

Jupyter Notebook

License

Last pushed

Oct 28, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/katelyn98/CorruptionRobustness"

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