Skip to content
/ lassl Public

[AAAI 2022] (ORAL) LaSSL: Label-Guided Self-Training for Semi-Supervised Learning

Notifications You must be signed in to change notification settings

ZhenZHAO/lassl

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

lassl

Submitted AAAI Paper.

Download your dataset to the folder data and create your own configuration file to the folder config.

We provide a template configuration file for CIFAR-10 with only 40 labels. The runing results using different random seeds are shown as follows.

Seed Top-1 Accuracy
1 95.28264331210191
2 95.10350318471338
3 93.5907643312102
4 95.5015923566879
5 95.8797770700637
Average 95.07165605095541

About

[AAAI 2022] (ORAL) LaSSL: Label-Guided Self-Training for Semi-Supervised Learning

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published