A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification
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 r...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Discrete Dynamics in Nature and Society |
| Online Access: | http://dx.doi.org/10.1155/2020/4706576 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832550429200744448 |
|---|---|
| author | Qinghe Zheng Mingqiang Yang Xinyu Tian Nan Jiang Deqiang Wang |
| author_facet | Qinghe Zheng Mingqiang Yang Xinyu Tian Nan Jiang Deqiang Wang |
| author_sort | Qinghe Zheng |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-7c02d81ff6514fd3a8b2c0983aefeb2e |
| institution | Kabale University |
| issn | 1026-0226 1607-887X |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Discrete Dynamics in Nature and Society |
| spelling | doaj-art-7c02d81ff6514fd3a8b2c0983aefeb2e2025-02-03T06:06:44ZengWileyDiscrete Dynamics in Nature and Society1026-02261607-887X2020-01-01202010.1155/2020/47065764706576A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image ClassificationQinghe Zheng0Mingqiang Yang1Xinyu Tian2Nan Jiang3Deqiang Wang4School of Information Science and Engineering, Shandong University, Qingdao 266237, ChinaSchool of Information Science and Engineering, Shandong University, Qingdao 266237, ChinaCollege of Mechanical and Electrical Engineering, Shandong Management University, Jinan 250357, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, ChinaSchool of Information Science and Engineering, Shandong University, Qingdao 266237, ChinaNowadays, 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.http://dx.doi.org/10.1155/2020/4706576 |
| spellingShingle | Qinghe Zheng Mingqiang Yang Xinyu Tian Nan Jiang Deqiang Wang A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification Discrete Dynamics in Nature and Society |
| title | A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification |
| title_full | A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification |
| title_fullStr | A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification |
| title_full_unstemmed | A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification |
| title_short | A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification |
| title_sort | full stage data augmentation method in deep convolutional neural network for natural image classification |
| url | http://dx.doi.org/10.1155/2020/4706576 |
| work_keys_str_mv | AT qinghezheng afullstagedataaugmentationmethodindeepconvolutionalneuralnetworkfornaturalimageclassification AT mingqiangyang afullstagedataaugmentationmethodindeepconvolutionalneuralnetworkfornaturalimageclassification AT xinyutian afullstagedataaugmentationmethodindeepconvolutionalneuralnetworkfornaturalimageclassification AT nanjiang afullstagedataaugmentationmethodindeepconvolutionalneuralnetworkfornaturalimageclassification AT deqiangwang afullstagedataaugmentationmethodindeepconvolutionalneuralnetworkfornaturalimageclassification AT qinghezheng fullstagedataaugmentationmethodindeepconvolutionalneuralnetworkfornaturalimageclassification AT mingqiangyang fullstagedataaugmentationmethodindeepconvolutionalneuralnetworkfornaturalimageclassification AT xinyutian fullstagedataaugmentationmethodindeepconvolutionalneuralnetworkfornaturalimageclassification AT nanjiang fullstagedataaugmentationmethodindeepconvolutionalneuralnetworkfornaturalimageclassification AT deqiangwang fullstagedataaugmentationmethodindeepconvolutionalneuralnetworkfornaturalimageclassification |