CASIA OpenIR  > 智能感知与计算
Local Semantic-Aware Deep Hashing With Hamming-Isometric Quantization
Wang, Yunbo1,2; Liang, Jian1,2; Cao, Dong1; Sun, Zhenan2,3
发表期刊IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN1057-7149
2019-06-01
卷号28期号:6页码:2665-2679
摘要

Hashing is a promising approach for compact storage and efficient retrieval of big data. Compared to the conventional hashing methods using handcrafted features, emerging deep hashing approaches employ deep neural networks to learn both feature representations and hash functions, which have been proven to be more powerful and robust in real-world applications. Currently, most of the existing deep hashing methods construct pairwise or triplet-wise constraints to obtain similar binary codes between a pair of similar data points or relatively similar binary codes within a triplet. However, we argue that some critical local structures have not been fully exploited. So, this paper proposes a novel deep hashing method named local semantic-aware deep hashing with Hamming-isometric quantization (LSDH), aiming to make full use of local similarity in hash function learning. Specifically, the potential semantic relation is exploited to robustly preserve local similarity of data in the Hamming space. In addition to reducing the error introduced by binary quantizing, a Hamming-isometric objective is designed to maximize the consistency of similarity between the pairwise binary-like features and corresponding binary codes pair, which is shown to be able to improve the quality of binary codes. Extensive experimental results on several benchmark datasets, including three singlelabel datasets and one multi-label dataset, demonstrate that the proposed LSDH achieves better performance than the latest state-of-the-art hashing methods.

关键词Image retrieval deep hashing similarity-preserving local structures Hamming-isometric
DOI10.1109/TIP.2018.2889269
关键词[WOS]IMAGE RETRIEVAL
收录类别SCI
语种英语
资助项目National Key Research and Development Program of China[2017YFC0821602] ; National Natural Science Foundation of China[61573360] ; National Natural Science Foundation of China[61427811] ; National Natural Science Foundation of China[U1836217] ; National Key Research and Development Program of China[2016YFB1001000] ; National Key Research and Development Program of China[2016YFB1001000] ; National Natural Science Foundation of China[U1836217] ; National Natural Science Foundation of China[61427811] ; National Natural Science Foundation of China[61573360] ; National Key Research and Development Program of China[2017YFC0821602]
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000462386000003
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类多模态智能
引用统计
被引频次:10[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/173211/23481
专题智能感知与计算
通讯作者Sun, Zhenan
作者单位1.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Inst Automat, Ctr Excellence Brain Sci & Intelligence Technol, Ctr Res Intelligent Percept & Comp, 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
Wang, Yunbo,Liang, Jian,Cao, Dong,et al. Local Semantic-Aware Deep Hashing With Hamming-Isometric Quantization[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2019,28(6):2665-2679.
APA Wang, Yunbo,Liang, Jian,Cao, Dong,&Sun, Zhenan.(2019).Local Semantic-Aware Deep Hashing With Hamming-Isometric Quantization.IEEE TRANSACTIONS ON IMAGE PROCESSING,28(6),2665-2679.
MLA Wang, Yunbo,et al."Local Semantic-Aware Deep Hashing With Hamming-Isometric Quantization".IEEE TRANSACTIONS ON IMAGE PROCESSING 28.6(2019):2665-2679.
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
LSDH_main_s.pdf(1445KB)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
[Wang, Yunbo]的文章
[Liang, Jian]的文章
[Cao, Dong]的文章
百度学术
百度学术中相似的文章
[Wang, Yunbo]的文章
[Liang, Jian]的文章
[Cao, Dong]的文章
必应学术
必应学术中相似的文章
[Wang, Yunbo]的文章
[Liang, Jian]的文章
[Cao, Dong]的文章
相关权益政策
暂无数据
收藏/分享
文件名: LSDH_main_s.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。