Deep Relative Attributes

doi:10.1109/TMM.2016.2582379

	Deep Relative Attributes
	Yang, Xiaoshan1 ; Zhang, Tianzhu1 ; Xu, Changsheng1 ; Yan, Shuicheng 2; Hossain, M. Shamim 3; Ghoneim, Ahmed 3,4
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
	2016-09-01
卷号	18 期号:9 页码:1832-1842
文章类型	Article
摘要	Relative attribute (RA) learning aims to learn the ranking function describing the relative strength of the attribute. Most of current learning approaches learn a linear ranking function for each attribute by use of the hand-crafted visual features. Different from the existing study, in this paper, we propose a novel deep relative attributes (DRA) algorithm to learn visual features and the effective nonlinear ranking function to describe the RA of image pairs in a unified framework. Here, visual features and the ranking function are learned jointly, and they can benefit each other. The proposed DRA model is comprised of five convolutional neural layers, five fully connected layers, and a relative loss function which contains the contrastive constraint and the similar constraint corresponding to the ordered image pairs and the unordered image pairs, respectively. To train the DRA model effectively, we make use of the transferred knowledge from the large scale visual recognition on ImageNet [1] to the RA learning task. We evaluate the proposed DRA model on three widely used datasets. Extensive experimental results demonstrate that the proposed DRA model consistently and significantly outperforms the state-of-the-art RA learning methods. On the public OSR, PubFig, and Shoes datasets, compared with the previous RA learning results [2], the average ranking accuracies have been significantly improved by about 8%, 9%, and 14%, respectively.
关键词	Deep Learning Relative Attributes (Ra)
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TMM.2016.2582379
关键词[WOS]	COMMUNITY-CONTRIBUTED PHOTOS ; OBJECT CLASSES ; RETRIEVAL
收录类别	SCI
语种	英语
项目资助者	Deanship of Scientific Research at King Saud University, Riyadh, Saudi Arabia(RGP-229)
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:000381437800013
引用统计	被引频次：65[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12644
专题	多模态人工智能系统全国重点实验室_多媒体计算
作者单位	1.National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 117576, Singapore 3.King Saud Univ, Coll Comp & Informat Sci, Dept Software Engn, Riyadh 11543, Saudi Arabia 4.Menoufia Univ, Coll Sci, Dept Comp Sci, Menoufia 32721, Egypt
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Yang, Xiaoshan,Zhang, Tianzhu,Xu, Changsheng,et al. Deep Relative Attributes[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2016,18(9):1832-1842.
APA	Yang, Xiaoshan,Zhang, Tianzhu,Xu, Changsheng,Yan, Shuicheng,Hossain, M. Shamim,&Ghoneim, Ahmed.(2016).Deep Relative Attributes.IEEE TRANSACTIONS ON MULTIMEDIA,18(9),1832-1842.
MLA	Yang, Xiaoshan,et al."Deep Relative Attributes".IEEE TRANSACTIONS ON MULTIMEDIA 18.9(2016):1832-1842.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Deep Relative Attrib（2778KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载