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
发表期刊IEEE TRANSACTIONS ON MULTIMEDIA
ISSN1520-9210
2019-06-01
卷号21期号:6页码:1551-1562
摘要

Existing 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.

关键词Iterative manifold embedding layer image retrieval incomplete data
DOI10.1109/TMM.2018.2883860
关键词[WOS]QUERY EXPANSION ; FEATURES
收录类别SCI
语种英语
资助项目National Natural Science Foundation of China[71621002] ; National Natural Science Foundation of China[71621002] ; National Natural Science Foundation of China[61601462] ; National Natural Science Foundation of China[61601462] ; National Natural Science Foundation of China[61531019] ; National Natural Science Foundation of China[61531019] ; National Natural Science Foundation of China[61531019] ; National Natural Science Foundation of China[61531019] ; National Natural Science Foundation of China[61601462] ; National Natural Science Foundation of China[61601462] ; National Natural Science Foundation of China[71621002] ; National Natural Science Foundation of China[71621002]
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:000469337400017
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类图像视频处理与分析
引用统计
被引频次:8[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/173211/24399
专题复杂系统管理与控制国家重点实验室_影像分析与机器视觉
通讯作者Wang, Chunheng
作者单位1.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
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
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.
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
IME_layer.pdf(4727KB)期刊论文作者接受稿开放获取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
[Xu, Jian]的文章
[Wang, Chunheng]的文章
[Qi, Chengzuo]的文章
百度学术
百度学术中相似的文章
[Xu, Jian]的文章
[Wang, Chunheng]的文章
[Qi, Chengzuo]的文章
必应学术
必应学术中相似的文章
[Xu, Jian]的文章
[Wang, Chunheng]的文章
[Qi, Chengzuo]的文章
相关权益政策
暂无数据
收藏/分享
文件名: IME_layer.pdf
格式: Adobe PDF
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。