Dynamic Multi-view Combination for Image Classification
Li,Chenghua3; Wang,Wanguo2; Liu,Fengyuan1,3; Guo,Zhenyu1,3
刊名Journal of Physics: Conference Series
2020-09-01
卷号1631期号:1
ISSN号1742-6588
DOI10.1088/1742-6596/1631/1/012125
英文摘要Abstract Multi-view learning is widely used in image classification tasks to better explore the discriminative information of different views. However, existing multi-view methods commonly rely on some pre-defined assumptions or fail to fully take advantage of the combination commonality between individual images. This paper presents an efficient dynamic multi-view combination approach to dynamically combine the discriminative power of different views. Specially, we firstly utilize a group of pre-trained CNNs to extract different views of an image. Secondly, we apply a dynamic gating module to the image, which will generate a weight vector of these views to model the image-level information for the multi-view learning. Finally, the weight vector and the views are combined for the classification. Experimental results and analysis on CIFAR-10 and ImageNet show the effectiveness of the proposed dynamic multi-view combination method (DMVC) for visual classification.
语种英语
出版者IOP Publishing
WOS记录号IOP:1742-6588-1631-1-012125
内容类型期刊论文
源URL[http://ir.ia.ac.cn/handle/173211/42192]  
专题类脑芯片与系统研究
作者单位1.University of Chinese Academy of Sciences, Beijing 100190, China
2.State Grid Intelligence Technology Co., Ltd., China
3.NLPR & AIRIA, Institute of Automation, Chinese Academy of Sciences, No. 95 Zhongguancun East Rd., Beijing 100190, China
推荐引用方式
GB/T 7714
Li,Chenghua,Wang,Wanguo,Liu,Fengyuan,et al. Dynamic Multi-view Combination for Image Classification[J]. Journal of Physics: Conference Series,2020,1631(1).
APA Li,Chenghua,Wang,Wanguo,Liu,Fengyuan,&Guo,Zhenyu.(2020).Dynamic Multi-view Combination for Image Classification.Journal of Physics: Conference Series,1631(1).
MLA Li,Chenghua,et al."Dynamic Multi-view Combination for Image Classification".Journal of Physics: Conference Series 1631.1(2020).
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace