Image-Text Dual Model for Small-Sample Image Classification

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

CORC > 兰州理工大学 > 兰州理工大学

	Image-Text Dual Model for Small-Sample Image Classification
	Zhu, Fangyi 4; Li, Xiaoxu 3,4; Ma, Zhanyu 4; Chen, Guang 4; Peng, Pai 2; Guo, Xiaowei 2; Chien, Jen-Tzung 1; Guo, Jun 4
	2017
关键词	Small-sample image classification Ensemble learning Deep convolutional neural network
卷号	772
DOI	10.1007/978-981-10-7302-1_46
页码	556-565
英文摘要	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 submodels, 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.
会议录	COMPUTER VISION, PT II
会议录出版者	SPRINGER-VERLAG SINGAPORE PTE LTD
会议录出版地	152 BEACH ROAD, #21-01/04 GATEWAY EAST, SINGAPORE, 189721, SINGAPORE
语种	英语
资助项目	Beijing Natural Science Foundation (BNSF)[4162044]
WOS研究方向	Computer Science
WOS记录号	WOS:000449831600046
内容类型	会议论文
源URL	[http://119.78.100.223/handle/2XXMBERH/36314]
专题	兰州理工大学
通讯作者	Ma, Zhanyu
作者单位	1.Natl Chiao Tung Univ, Dept Elect & Comp Engn, Hsinchu, Taiwan 2.Tecent Technol, Youtu Lab, Shanghai, Peoples R China 3.Lanzhou Univ Technol, Sch Comp & Commun, Lanzhou, Gansu, Peoples R China 4.Beijing Univ Posts & Telecommun, Pattern Recognit & Intelligent Syst Lab, Beijing, Peoples R China
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]. 见:.