模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2018, Vol. 31 Issue (7): 625-633    DOI: 10.16451/j.cnki.issn1003-6059.201807005
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Scene Classification with Adaptive Learning Rate and Sample Training Mode
CHU Jun1, SU Yawei2, WANG Lu1
1.Institute of Computer Vision, Nanchang Hangkong University, Nanchang 330063
2.School of Information Engineering, Nanchang Hangkong University, Nanchang 330063

Download: PDF (0 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  In scene classification based on convolutional neural network, over-fitting is caused due to the large number of network training and poor convergence performance with the small training dataset. To eliminate the negative effect, an algorithm for scene classification with adaptive learning rate and sample training mode is proposed. The network learning rate is adaptively adjusted on the framework of convolutional neural network according to the variation of the error function in the network training. When the error function changes slightly, the learning rate of the batch is unchanged. When the error function changes more remarkably, the variation of the learning rate is inversely proportional to the variation of the error function. Meanwhile, according to the network output, the sample training mode is switched, and the inaccurately recognized images are emphatically trained. The experimental results on Scene-15 and Cifar-10 scene datasets show that the proposed method improves the convergence of neural networks and effectively improves the classification accuracy, especially the classification accuracy of complex scenes such as indoor scenes.
Key wordsScene Classification      Convolutional Neural Network      Adaptive Learning Rate      Adaptive Sample Training     
Received: 27 March 2018     
ZTFLH: TP 391.4  
Fund:Supported by National Natural Science Foundation of China(No.61663031、61661036), Key Research and Development Plan Project of Jiangxi Province(No.20161BBE50085)
Corresponding Authors: CHU Jun(Corresponding author), Ph.D., professor. Her research interests include image processing and analysis, pattern recognition and computer vision.   
About author:: SU Yawei, master student. His research interests include image classification and deep learning.WANG Lu, master, lecturer. Her research interests include image processing and pattern recognition.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
CHU Jun
SU Yawei
WANG Lu
Cite this article:   
CHU Jun,SU Yawei,WANG Lu. Scene Classification with Adaptive Learning Rate and Sample Training Mode[J]. , 2018, 31(7): 625-633.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201807005      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2018/V31/I7/625
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn