Deep Convolutional Neural Networks Based on Image Data Augmentation for Visual Object Recognition

被引:1
作者
Jayech, Khaoula [1 ]
机构
[1] Univ Sousse, Ecole Natl Ingn Sousse, LATIS Lab Adv Technol & Intelligent Syst, Sousse 4023, Tunisia
来源
INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2019, PT I | 2019年 / 11871卷
关键词
Deep learning; DCNN; Image data augmentation; Object recognition;
D O I
10.1007/978-3-030-33607-3_51
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep Neural Networks (DNNs) have achieved a great success in machine learning. Among a lot of DNN structures, Deep Convolutional Neural Networks (DCNNs) are currently the main tool in the state-of-the-art variety of classification tasks like visual object recognition and handwriting and speech recognition. Despite wide perspectives, DCNNs have still some challenges to deal with. In previous work, we demonstrated the effectiveness of using some regularization techniques such as the dropout to enhance the performance of DCNNs. However, DCNNs need enough training data or even a class balance within datasets to conduct better results. To resolve this problem, some researchers have evoked different data augmentation approaches. This paper presents an extension of a later study. In this work, we conducted and compared the results of many experiments on CIFAR-10, STL-10 and SVHN using variant techniques of data augmentation combined with regularization techniques. The analysis results show that with the right use of data augmentation approaches, it is possible to achieve good results and outperform the state-of-the-art in this field.
引用
收藏
页码:476 / 485
页数:10
相关论文
共 22 条
[1]   Very Deep Neural Networks for Hindi/Arabic Offline Handwritten Digit Recognition [J].
Almodfer, Rolla ;
Xiong, Shengwu ;
Mudhsh, Mohammed ;
Duan, Pengfei .
NEURAL INFORMATION PROCESSING (ICONIP 2017), PT II, 2017, 10635 :450-459
[2]   Growing random forest on deep convolutional neural networks for scene categorization [J].
Bai, Shuang .
EXPERT SYSTEMS WITH APPLICATIONS, 2017, 71 :279-287
[3]  
Devries Terrance, 2017, arXiv
[4]   Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels [J].
Han, Bo ;
Yao, Quanming ;
Yu, Xingrui ;
Niu, Gang ;
Xu, Miao ;
Hu, Weihua ;
Tsang, Ivor W. ;
Sugiyama, Masashi .
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
[5]   Regularized Deep Convolutional Neural Networks for Feature Extraction and Classification [J].
Jayech, Khaoula .
NEURAL INFORMATION PROCESSING (ICONIP 2017), PT II, 2017, 10635 :431-439
[6]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90
[7]  
Li DP, 2015, PROC CVPR IEEE, P213, DOI 10.1109/CVPR.2015.7298617
[8]   Deep Convolutional Neural Networks for Classifying Body Constitution [J].
Li, Haiteng ;
Xu, Bin ;
Wang, Nanyue ;
Liu, Jia .
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT II, 2016, 9887 :128-135
[9]  
Liang M., 2015, PROC CVPR IEEE, P3367, DOI [DOI 10.1109/CVPR.2015.7298958, 10.1109/CVPR.2015.7298958]
[10]   Soft-Margin Softmax for Deep Classification [J].
Liang, Xuezhi ;
Wang, Xiaobo ;
Lei, Zhen ;
Liao, Shengcai ;
Li, Stan Z. .
NEURAL INFORMATION PROCESSING (ICONIP 2017), PT II, 2017, 10635 :413-421