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

DOI PDF XML 1 Citations
  • Qinghe Zheng
    School of Information Science and Engineering, Shandong University, Qingdao 266237, China
  • Mingqiang Yang
    School of Information Science and Engineering, Shandong University, Qingdao 266237, China
  • Xinyu Tian
    College of Mechanical and Electrical Engineering, Shandong Management University, Jinan 250357, China
  • Nan Jiang
    School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, China
  • Deqiang Wang
    School of Information Science and Engineering, Shandong University, Qingdao 266237, China

Description

<jats:p>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.</jats:p>

Journal

Citations (1)*help

See more

Report a problem

Back to top