Deep Category-Level and Regularized Hashing With Global Semantic Similarity Learning | |
Chen, Yaxiong1,2; Lu, Xiaoqiang2 | |
刊名 | IEEE TRANSACTIONS ON CYBERNETICS |
2021-12 | |
卷号 | 51期号:12页码:6240-6252 |
关键词 | Semantics Binary codes Image retrieval Force Machine learning Cybernetics Benchmark testing Category-level semantics deep feature similarity deep hashing image retrieval |
ISSN号 | 2168-2267;2168-2275 |
DOI | 10.1109/TCYB.2020.2964993 |
产权排序 | 1 |
英文摘要 | The hashing technique has been extensively used in large-scale image retrieval applications due to its low storage and fast computing speed. Most existing deep hashing approaches cannot fully consider the global semantic similarity and category-level semantic information, which result in the insufficient utilization of the global semantic similarity for hash codes learning and the semantic information loss of hash codes. To tackle these issues, we propose a novel deep hashing approach with triplet labels, namely, deep category-level and regularized hashing (DCRH), to leverage the global semantic similarity of deep feature and category-level semantic information to enhance the semantic similarity of hash codes. There are four contributions in this article. First, we design a novel global semantic similarity constraint about the deep feature to make the anchor deep feature more similar to the positive deep feature than to the negative deep feature. Second, we leverage label information to enhance category-level semantics of hash codes for hash codes learning. Third, we develop a new triplet construction module to select good image triplets for effective hash functions learning. Finally, we propose a new triplet regularized loss (Reg-L) term, which can force binary-like codes to approximate binary codes and eventually minimize the information loss between binary-like codes and binary codes. Extensive experimental results in three image retrieval benchmark datasets show that the proposed DCRH approach achieves superior performance over other state-of-the-art hashing approaches. |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000733232400054 |
内容类型 | 期刊论文 |
源URL | [http://ir.opt.ac.cn/handle/181661/95621] |
专题 | 西安光学精密机械研究所_光学影像学习与分析中心 |
通讯作者 | Lu, Xiaoqiang |
作者单位 | 1.Chinese Academy of Sciences University of Chinese Academy of Sciences, CAS 2.Chinese Academy of Sciences Xi'an Institute of Optics & Precision Mechanics, CAS |
推荐引用方式 GB/T 7714 | Chen, Yaxiong,Lu, Xiaoqiang. Deep Category-Level and Regularized Hashing With Global Semantic Similarity Learning[J]. IEEE TRANSACTIONS ON CYBERNETICS,2021,51(12):6240-6252. |
APA | Chen, Yaxiong,&Lu, Xiaoqiang.(2021).Deep Category-Level and Regularized Hashing With Global Semantic Similarity Learning.IEEE TRANSACTIONS ON CYBERNETICS,51(12),6240-6252. |
MLA | Chen, Yaxiong,et al."Deep Category-Level and Regularized Hashing With Global Semantic Similarity Learning".IEEE TRANSACTIONS ON CYBERNETICS 51.12(2021):6240-6252. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论