Skip to content

ana-srin/STACI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

STACI

This study adapts the Soft Teacher semi-supervised learning method, originally for object detection, to image classification, aiming to enhance accuracy with limited labeled data. STACI uses a student-teacher structure with data augmentation and EMA for prediction consistency, demonstrating the benefits of soft labels and consistency regularization in a semi-supervised context.

Here, the CIFAR-10 dataset is used for benchmarking purposes.

Code coming up soon.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published