CASIA OpenIR
Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-Scale Image Retrieval
Xu, Jian1,2; Wang, Chunheng2; Qi, Chengzuo1,2; Shi, Cunzhao2; Xiao, Baihua2
Source PublicationIEEE TRANSACTIONS ON MULTIMEDIA
ISSN1520-9210
2019-06-01
Volume21Issue:6Pages:1551-1562
Corresponding AuthorWang, Chunheng(chunheng.wang@ia.ac.cn)
AbstractExisting manifold learning methods are not appropriate for image retrieval tasks, because most of them are unable to process query images and they have much greater computational cost especially for large-scale database. Therefore, we propose the iterative manifold embedding (IME) layer, of which the weights are learned offline by an unsupervised strategy, to explore the intrinsic manifolds by incomplete data. On the large-scale database that contains 27 000 images, the IME layer is more than 120 times faster than other manifold learning methods to embed the original representations at query time. We embed the original descriptors of database images that lie on manifold in a high-dimensional space into manifold-based representations iteratively to generate the IME representations in an offline learning stage. According to the original descriptors and the IME representations of database images, we estimate the weights of the IME layer by ridge regression. In the online retrieval stage, we employ the IME layer to map the original representation of a query image with an ignorable time cost (2 ms per image). We experiment on five public standard datasets for image retrieval. The proposed IME layer significantly outperforms the related dimension reduction methods and manifold learning methods. Without postprocessing, our IME layer achieves a boost in the performance of state-of-the-art image retrieval methods with postprocessing on most datasets, and needs less computational cost.
KeywordIterative manifold embedding layer image retrieval incomplete data
DOI10.1109/TMM.2018.2883860
WOS KeywordQUERY EXPANSION ; FEATURES
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[61531019] ; National Natural Science Foundation of China[61601462] ; National Natural Science Foundation of China[71621002]
Funding OrganizationNational Natural Science Foundation of China
WOS Research AreaComputer Science ; Telecommunications
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS IDWOS:000469337400017
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/24399
Collection中国科学院自动化研究所
Corresponding AuthorWang, Chunheng
Affiliation1.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
2.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Xu, Jian,Wang, Chunheng,Qi, Chengzuo,et al. Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-Scale Image Retrieval[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2019,21(6):1551-1562.
APA Xu, Jian,Wang, Chunheng,Qi, Chengzuo,Shi, Cunzhao,&Xiao, Baihua.(2019).Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-Scale Image Retrieval.IEEE TRANSACTIONS ON MULTIMEDIA,21(6),1551-1562.
MLA Xu, Jian,et al."Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-Scale Image Retrieval".IEEE TRANSACTIONS ON MULTIMEDIA 21.6(2019):1551-1562.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xu, Jian]'s Articles
[Wang, Chunheng]'s Articles
[Qi, Chengzuo]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xu, Jian]'s Articles
[Wang, Chunheng]'s Articles
[Qi, Chengzuo]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xu, Jian]'s Articles
[Wang, Chunheng]'s Articles
[Qi, Chengzuo]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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