Skip to content

Investigating alternative auxiliary tasks in image classification.

Notifications You must be signed in to change notification settings

ChenLiu-1996/Classification_Auxiliary_Task

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Alternative Auxiliary Task for Image Classification

Chen Liu

Image reconstruction has long been treated as a valid and effective auxiliary task to facilitate the learning of useful and meaningful features for image classification. We are re-thinking this paradigm to see if we can use other auxiliary tasks that either emperically yields better performances on the primary task (classification), or poses different constraints on the learning process.

Please feel free to use this repository as you like to do your own experiments, try out other auxiliary tasks, test on different primary tasks, etc.

Our paper

The preliminary work has been submitted to ArXiv. "Fourier Transform Approximation as an Auxiliary Task for Image Classification". If you have suggestions on what experiements/analyses to perform to further improve this manuscript, please let us know.

@article{liu2021fourier,
  title={Fourier Transform Approximation as an Auxiliary Task for Image Classification},
  author={Liu, Chen},
  journal={arXiv e-prints},
  pages={arXiv--2106},
  year={2021}
}

Environment Setup

We used anaconda environment. The step-by-step instructions are written in dependencies.txt.

About

Investigating alternative auxiliary tasks in image classification.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages