STaDA: Style Transfer as Data Augmentation
This work addresses the challenge of data scarcity in computer vision, offering a potential solution to reduce the need for extensive labeled data collection, though it is incremental as it builds on existing style transfer techniques.
The paper tackled the problem of limited labeled data for training deep CNNs by using neural style transfer as a data augmentation method, resulting in a 2% improvement in image classification accuracy from 83% to 85% on Caltech datasets with VGG16.
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.