OPT OpenIR  > 光谱成像技术研究室
Discrete Spectral Hashing for Efficient Similarity Retrieval
Hu, Di1; Nie, Feiping1; Li, Xuelong2
作者部门光学影像学习与分析中心
2019-03
发表期刊IEEE Transactions on Image Processing
ISSN10577149
卷号28期号:3
产权排序2
摘要

To meet the required huge data analysis, organization and storage demand, hashing technique has got a lot of attention as it aims to learn efficient binary representation from the original high-dimensional data. In this paper, we focus on the unsupervised spectral hashing due to its effective manifold embedding. Existing spectral hashing methods mainly suffer from two problems, i.e., the inefficient spectral candidate and intractable binary constraint for spectral analysis. To overcome these two problems, we propose to employ spectral rotation to seek better spectral solution and adopt the alternating projection algorithm to settle the complex code constraints, which are therefore named as Spectral Hashing with Spectral Rotation (SHSR) and Alternating Discrete Spectral Hashing (ADSH), respectively. To enjoy the merits of both methods, the spectral rotation technique is finally combined with the original spectral objective, which aims to simultaneously learn better spectral solution and more efficient discrete codes and is called as Discrete Spectral Hashing (DSH). Further, efficient optimization algorithms are also provided, which just take comparable time complexity to existing hashing methods. To evaluate the proposed three methods, extensive comparison experiments and studies are conducted on four large-scale datasets for the image retrieval task, and the noticeable performance beats several state-of-theart spectral hashing methods on different evaluation metrics. IEEE

关键词Spectral Rotation Discrete Spectral Hashing
DOI10.1109/TIP.2018.2875312
收录类别SCI ; EI
语种英语
WOS记录号WOS:000448657400003
EI入藏号20184205949164
引用统计
被引频次:28[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.opt.ac.cn/handle/181661/30679
专题光谱成像技术研究室
作者单位1.School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China, 710072.;
2.Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, Shaanxi, P. R. China, 710119.
推荐引用方式
GB/T 7714
Hu, Di,Nie, Feiping,Li, Xuelong. Discrete Spectral Hashing for Efficient Similarity Retrieval[J]. IEEE Transactions on Image Processing,2019,28(3).
APA Hu, Di,Nie, Feiping,&Li, Xuelong.(2019).Discrete Spectral Hashing for Efficient Similarity Retrieval.IEEE Transactions on Image Processing,28(3).
MLA Hu, Di,et al."Discrete Spectral Hashing for Efficient Similarity Retrieval".IEEE Transactions on Image Processing 28.3(2019).
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Discrete Spectral Ha(1938KB)期刊论文出版稿限制开放CC BY-NC-SA请求全文
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
[Hu, Di]的文章
[Nie, Feiping]的文章
[Li, Xuelong]的文章
百度学术
百度学术中相似的文章
[Hu, Di]的文章
[Nie, Feiping]的文章
[Li, Xuelong]的文章
必应学术
必应学术中相似的文章
[Hu, Di]的文章
[Nie, Feiping]的文章
[Li, Xuelong]的文章
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。