Image-text dual model for small-sample image classification

doi:10.1007/978-981-10-7302-1_46

	Image-text dual model for small-sample image classification
	Zhu, Fangyi 1; Li, Xiaoxu 1,2; Ma, Zhanyu 1; Chen, Guang 1; Peng, Pai 3; Guo, Xiaowei 3; Chien, Jen-Tzung 4; Guo, Jun 1
	2017
会议名称	2nd Chinese Conference on Computer Vision, CCCV 2017
会议录名称	Communications in Computer and Information Science
卷号	772
页码	556-565
会议日期	October 11, 2017 - October 14, 2017
会议地点	Tianjin, China
出版者	Springer Verlag
摘要	Small-sample classification is a challenging problem in computer vision and has many applications. In this paper, we propose an image-text dual model to improve the classification performance on small-sample dataset. The proposed dual model consists of two sub-models, an image classification model and a text classification model. After training the sub-models respectively, we design a novel method to fuse the two sub-models rather than simply combining the two models’ results. Our image-text dual model aims to utilize the text information to overcome the problem of training deep models on small-sample datasets. To demonstrate the effectiveness of the proposed dual model, we conduct extensive experiments on LabelMe and UIUC-Sports. Experimental results show that our model is superior to other models. In conclusion, our proposed model can achieve the highest image classification accuracy among all the referred models on LabelMe and UIUC-Sports. © Springer Nature Singapore Pte Ltd. 2017.
关键词	Classification (of information) Computer vision Deep neural networks Image enhancement Neural networks Sports Text processing Classification accuracy Classification performance Convolutional neural network Ensemble learning Image texts Small samples Text classification models Text information
DOI	10.1007/978-981-10-7302-1_46
收录类别	EI
语种	英语
EI入藏号	20175104550047
EI主题词	Image classification
ISSN	18650929
来源库	Compendex
分类代码	461.3 Biomechanics, Bionics and Biomimetics - 716.1 Information Theory and Signal Processing - 723.5 Computer Applications - 903.1 Information Sources and Analysis
引用统计	被引频次[WOS]：0 [WOS记录] [WOS相关记录]
文献类型	会议论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/118154
专题	兰州理工大学
作者单位	1.Pattern Recognition and Intelligent System Lab, Beijing University of Posts and Telecommunications, Beijing, China; 2.School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China; 3.Youtu Lab, Tecent Technology, Shanghai, China; 4.Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu City, Taiwan
推荐引用方式 GB/T 7714	Zhu, Fangyi,Li, Xiaoxu,Ma, Zhanyu,et al. Image-text dual model for small-sample image classification[C]:Springer Verlag,2017:556-565.