STaDA: Style Transfer as Data Augmentation

Xu Zheng, Tejo Chalasani, Koustav Ghosal, Sebastian Lutz, Aljosa Smolic

2019

Abstract

The success of training deep Convolutional Neural Networks (CNNs) heavily depends on a significant amount of labelled data. Recent research has found that neural style transfer algorithms can apply the artistic style of one image to another image without changing the latter’s high-level semantic content, which makes it feasible to employ neural style transfer as a data augmentation method to add more variation to the training dataset. The contribution of this paper is a thorough evaluation of the effectiveness of the neural style transfer as a data augmentation method for image classification tasks. We explore the state-of-the-art neural style transfer algorithms and apply them as a data augmentation method on Caltech 101 and Caltech 256 dataset, where we found around 2% improvement from 83% to 85% of the image classification accuracy with VGG16, compared with traditional data augmentation strategies. We also combine this new method with conventional data augmentation approaches to further improve the performance of image classification. This work shows the potential of neural style transfer in computer vision field, such as helping us to reduce the difficulty of collecting sufficient labelled data and improve the performance of generic image-based deep learning algorithms.

Paper Citation

in Harvard Style

Zheng X., Chalasani T., Ghosal K., Lutz S. and Smolic A. (2019). STaDA: Style Transfer as Data Augmentation. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 107-114. DOI: 10.5220/0007353401070114

in Bibtex Style

@conference{visapp19,
author={Xu Zheng and Tejo Chalasani and Koustav Ghosal and Sebastian Lutz and Aljosa Smolic},
title={STaDA: Style Transfer as Data Augmentation},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP},
year={2019},
pages={107-114},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007353401070114},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP
TI - STaDA: Style Transfer as Data Augmentation
SN - 978-989-758-354-4
AU - Zheng X.
AU - Chalasani T.
AU - Ghosal K.
AU - Lutz S.
AU - Smolic A.
PY - 2019
SP - 107
EP - 114
DO - 10.5220/0007353401070114
PB - SciTePress