Skip to content

Code release for ``Stochastic Consensus: Enhancing Semi-Supervised Learning with Consistency of Stochastic Classifiers'' accepted by ECCV 2022.

License

Notifications You must be signed in to change notification settings

Gorilla-Lab-SCUT/STOCO

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 
 
 

Repository files navigation

STOCO

Code release for ``Stochastic Consensus: Enhancing Semi-Supervised Learning with Consistency of Stochastic Classifiers'' accepted by ECCV 2022.

Project Page $\cdot$ PDF Download

Requirements

  • python 3.6.4
  • pytorch 1.4.0
  • torchvision 0.5.0

Data preparation

The references of the used datasets are included in the paper.

Model training

  1. Install necessary python packages.
  2. Replace root and dataset in run.sh with those in one's own system.
  3. Run command sh run.sh.

The results are saved in the folder ./results/.

Paper citation

@InProceedings{STOCO,
author={Tang, Hui
and Sun, Lin
and Jia, Kui},
title={Stochastic Consensus: Enhancing Semi-Supervised Learning with Consistency of Stochastic Classifiers},
booktitle={Computer Vision -- ECCV 2022},
year={2022},
pages={330-346},
}

About

Code release for ``Stochastic Consensus: Enhancing Semi-Supervised Learning with Consistency of Stochastic Classifiers'' accepted by ECCV 2022.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 98.6%
  • Shell 1.4%