Research Area:  Machine Learning

Abstract:

On the visual side of computer science, image data is very important in the training of neural network models. Sufficient training data can alleviate the over-fitting problem of the model during training and help the model obtain the optimal solution. However, in many computer vision assignments, it is not easy and costly to obtain sufficient training samples. Therefore, image augmentation has become a commonly used method to increase training samples. Generative Adversarial Network (GAN) is a generative method of machine learning that can generate realistic images and provide a new solution for image augmentation. This article first introduces image augmentation and its commonly used four types of methods. Secondly, the basic principles of GAN and its direct and integrated methods in image augmentation are introduced, and the typical methods used to calculate whether the images from the networks meets the requirements; then the research status of GAN in image augmentation is analyzed. Finally, the problems and development trends of GAN model in image augmentation are summarized and prospected.

Keywords:  
Image Augmentation
Generative Adversarial Network
Deep Learning
Machine Learning

Author(s) Name:  Fei Yue, Chao Zhang, MingYang Yuan, Chen Xu and YaLin Song

Publisher name:  IOP Publishing Ltd

DOI:  10.1088/1742-6596/2203/1/012052

Volume Information:  

Paper Link:   https://iopscience.iop.org/article/10.1088/1742-6596/2203/1/012052/meta