Image Classification Based on Mixed Deep Learning Model Transfer Learning

Authors

Xiangbin Shi, 1. Department of Computer, Shenyang Aerospace University, Shenyang 110136, China;;2. Liaoning General Aviation Key Laboratory, Shenyang Aerospace University, Shenyang 110136, China;;3. College of Information, Liaoning University, Shenyang 110036, China;
Xuejian Fang, 3. College of Information, Liaoning University, Shenyang 110036, China;
Deyuan Zhang, 1. Department of Computer, Shenyang Aerospace University, Shenyang 110136, China;;
Zhongqiang Guo, 3. College of Information, Liaoning University, Shenyang 110036, China;

Abstract

Abstract: In order to obtain high discrimination image representations in limited amount of datasets, the method based on mixed deep transfer learning model was proposed. When trained CNNs transferred to the target datasets, fully-connected layers were replaced by RBM layers. The method retrained the RBM layers and Softmax classifier, then fine-tuned the mixed model with backpropagation algorithm. The RBM layers not only fully connected whole feature maps, but also learned the target datasets' statistical features in the view of the biggest logarithmic likelihood, to eliminate the effects caused by the content differences between datasets. The experimental results show that the method has improved the accuracy of image classification, outperforming other methods on Pascal VOC2007 and Caltech101 datasets.

Recommended Citation

Shi, Xiangbin; Fang, Xuejian; Zhang, Deyuan; and Guo, Zhongqiang (2020) "Image Classification Based on Mixed Deep Learning Model Transfer Learning," Journal of System Simulation: Vol. 28: Iss. 1, Article 23.
Available at: https://dc-china-simulation.researchcommons.org/journal/vol28/iss1/23

First Page

167

Revised Date

2015-07-30

DOI Link

https://doi.org/

Last Page

173

CLC

TP391.9

Recommended Citation

Shi Xiangbin, Fang Xuejian, Zhang Deyuan, Guo Zhongqiang. Image Classification Based on Mixed Deep Learning Model Transfer Learning[J]. Journal of System Simulation, 2016, 28(1): 167-173.