Deep Relative Attributes
Yang, Xiaoshan1; Zhang, Tianzhu1; Xu, Changsheng1; Yan, Shuicheng2; Hossain, M. Shamim3; Ghoneim, Ahmed3,4
2016-09-01
发表期刊IEEE TRANSACTIONS ON MULTIMEDIA
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
DOI10.1109/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
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/12644
专题模式识别国家重点实验室_多媒体计算与图形学
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
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
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yang, Xiaoshan]的文章
[Zhang, Tianzhu]的文章
[Xu, Changsheng]的文章
百度学术
百度学术中相似的文章
[Yang, Xiaoshan]的文章
[Zhang, Tianzhu]的文章
[Xu, Changsheng]的文章
必应学术
必应学术中相似的文章
[Yang, Xiaoshan]的文章
[Zhang, Tianzhu]的文章
[Xu, Changsheng]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Deep Relative Attributes
格式: Unknown
此文件暂不支持浏览
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。