A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification

• Published in: Discrete dynamics in nature and society Vol. 2020; no. 2020; pp. 1 - 11
• Main Authors: Jiang, Nan, Tian, Xinyu, Yang, Mingqiang, Zheng, Qinghe, Wang, Deqiang
• Format: Journal Article
• Language: English
• Published: Cairo, Egypt Hindawi Publishing Corporation 2020; Hindawi; John Wiley & Sons, Inc; Hindawi Limited
• Subjects: Artificial neural networks; Back propagation; Big Data; Cable television broadcasting industry; Classification; Computer vision; Data augmentation; Datasets; Deep learning; Image classification; Machine learning; Machine vision; Methods; Neural networks; Noise; Optimization; Propagation; Regularization methods; Training; United States; China
• ISSN: 1026-0226; 1607-887X
• DOI: 10.1155/2020/4706576

Nowadays, deep learning has achieved remarkable results in many computer vision related tasks, among which the support of big data is essential. In this paper, we propose a full stage data augmentation framework to improve the accuracy of deep convolutional neural networks, which can also play the role of implicit model ensemble without introducing additional model training costs. Simultaneous data augmentation during training and testing stages can ensure network optimization and enhance its generalization ability. Augmentation in two stages needs to be consistent to ensure the accurate transfer of specific domain information. Furthermore, this framework is universal for any network architecture and data augmentation strategy and therefore can be applied to a variety of deep learning based tasks. Finally, experimental results about image classification on the coarse-grained dataset CIFAR-10 (93.41%) and fine-grained dataset CIFAR-100 (70.22%) demonstrate the effectiveness of the framework by comparing with state-of-the-art results.