CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算与图形学
Deep Relative Attributes
Yang, Xiaoshan1; Zhang, Tianzhu1; Xu, Changsheng1; Yan, Shuicheng2; Hossain, M. Shamim3; Ghoneim, Ahmed3,4
AbstractRelative 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.
KeywordDeep Learning Relative Attributes (Ra)
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Funding OrganizationDeanship of Scientific Research at King Saud University, Riyadh, Saudi Arabia(RGP-229)
WOS Research AreaComputer Science ; Telecommunications
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS IDWOS:000381437800013
Citation statistics
Cited Times:8[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Affiliation1.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
Recommended Citation
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.
Files in This Item: Download All
File Name/Size DocType Version Access License
Deep Relative Attrib(2778KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang, Xiaoshan]'s Articles
[Zhang, Tianzhu]'s Articles
[Xu, Changsheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang, Xiaoshan]'s Articles
[Zhang, Tianzhu]'s Articles
[Xu, Changsheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang, Xiaoshan]'s Articles
[Zhang, Tianzhu]'s Articles
[Xu, Changsheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Deep Relative Attributes
Format: Unknown
This file does not support browsing at this time
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.