STaDA: Style Transfer as Data Augmentation

TL;DR

This paper evaluates neural style transfer as a data augmentation technique for image classification, demonstrating around 2% accuracy improvement on Caltech datasets and potential to enhance deep learning performance.

Contribution

It provides a thorough evaluation of neural style transfer for data augmentation in image classification, combining it with traditional methods for improved results.

Findings

Neural style transfer improves classification accuracy by about 2%.

Combining style transfer with traditional augmentation yields further gains.

Style transfer reduces data collection challenges in computer vision.

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.