chengtan9907/Hyperspherical-Consistency-Regularization

The official implementation of the CVPR'2022 paper Hyperspherical Consistency Regularization.

19
/ 100
Experimental

This is a technical deep learning regularization method for researchers and practitioners working with deep learning models. It helps improve the robustness and data efficiency of deep learning models, particularly in scenarios where labeled data is scarce. By taking the outputs from a deep learning classifier and a projection head, it applies a consistency regularization to enhance model performance. This is for machine learning engineers and researchers.

No commits in the last 6 months.

Use this if you are developing or training deep learning models and need a method to improve their robustness or performance when you have limited labeled data, or you are exploring self-supervised learning techniques.

Not ideal if you are an end-user looking for a pre-built solution for a specific task or if you do not have a strong understanding of deep learning model architectures and training processes.

deep-learning-research self-supervised-learning model-regularization computer-vision machine-learning-engineering
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

29

Forks

1

Language

Python

License

Last pushed

Jun 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/chengtan9907/Hyperspherical-Consistency-Regularization"

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