Deep Semantic Reconstruction Hashing for Similarity Retrieval

doi:10.1109/TCSVT.2020.2974768

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	Deep Semantic Reconstruction Hashing for Similarity Retrieval
	Wang, Yunbo 3,4; Ou, Xianfeng 2; Liang, Jian 1; Sun, Zhenan 3,4,5
刊名	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2021
卷号	31 期号:1 页码:387-400
关键词	Semantics Quantization (signal) Binary codes Image reconstruction Hamming distance Marine vehicles Airplanes Deep hashing high-level semantic similarity similarity-preserving quantization similarity retrieval
ISSN号	1051-8215
DOI	10.1109/TCSVT.2020.2974768
通讯作者	Sun, Zhenan(znsun@nlpr.ia.ac.cn)
英文摘要	Hashing has shown enormous potentials in preserving semantic similarity for large-scale data retrieval. Existing methods widely retain the similarity within two binary codes towards their discrete semantic affinity, i.e., 1 or -1. However, such a discrete reconstruction approach has obvious drawbacks. First, two unrelated dissimilar samples would have similar binary codes when both of them are the most dissimilar with an anchor sample. Second, the fine-grained semantic similarity cannot be shown in the generated binary codes among data with multiple semantic concepts. Furthermore, existing approaches generally adopt a point-wise error-minimizing strategy to enforce the real-valued codes close to its associated discrete codes, resulting in the well-learned paired semantic similarity being unintentionally damaged when performing quantization. To address these issues, we propose a novel deep hashing method with pairwise similarity-preserving quantization constraint, termed Deep Semantic Reconstruction Hashing (DSRH), which defines a high-level semantic affinity within each data pair to learn compact binary codes. Specifically, DSRH is expected to learn the specific binary codes whose similarity can reconstruct their high-level semantic similarity. Besides, we adopt a pairwise similarity-preserving quantization constraint instead of the traditional point-wise quantization technique, which is conducive to maintain the well-learned paired semantic similarity when performing quantization. Extensive experiments are conducted on four representative image retrieval benchmarks, and the proposed DSRH outperforms the state-of-the-art deep-learning methods with respect to different evaluation metrics.
资助项目	National Key Research and Development Program of China[2016YFB1001000] ; National Key Research and Development Program of China[2016YFB1001001] ; National Key Research and Development Program of China[2017YFC0821602] ; National Natural Science Foundation of China[U1836217] ; National Natural Science Foundation of China[61427811] ; National Natural Science Foundation of China[61573360] ; National Natural Science Foundation of China[61721004]
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000607384300030
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/42556]
专题	自动化研究所_智能感知与计算研究中心
通讯作者	Sun, Zhenan
作者单位	1.Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 117583, Singapore 2.Hunan Inst Sci & Technol, Sch Sci Informat & Engn, Yueyang 414006, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Ctr Res Intelligent Percept & Comp, Beijing 100190, Peoples R China 5.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wang, Yunbo,Ou, Xianfeng,Liang, Jian,et al. Deep Semantic Reconstruction Hashing for Similarity Retrieval[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2021,31(1):387-400.
APA	Wang, Yunbo,Ou, Xianfeng,Liang, Jian,&Sun, Zhenan.(2021).Deep Semantic Reconstruction Hashing for Similarity Retrieval.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,31(1),387-400.
MLA	Wang, Yunbo,et al."Deep Semantic Reconstruction Hashing for Similarity Retrieval".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 31.1(2021):387-400.