Knowledge Commons of Institute of Automation,CAS
Adversarial Binary Mutual Learning for Semi-Supervised Deep Hashing | |
Wang, Guanan1,2; Hu, Qinghao3; Yang, Yang3; Cheng, Jian3; Hou, Zeng-Guang4,5,6,7 | |
发表期刊 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS |
ISSN | 2162-237X |
2021-03-06 | |
页码 | 15 |
通讯作者 | Hou, Zeng-Guang(zengguang.hou@ia.ac.cn) |
摘要 | Hashing is a popular search algorithm for its compact binary representation and efficient Hamming distance calculation. Benefited from the advance of deep learning, deep hashing methods have achieved promising performance. However, those methods usually learn with expensive labeled data but fail to utilize unlabeled data. Furthermore, the traditional pairwise loss used by those methods cannot explicitly force similar/dissimilar pairs to small/large distances. Both weaknesses limit existing methods' performance. To solve the first problem, we propose a novel semi-supervised deep hashing model named adversarial binary mutual learning (ABML). Specifically, our ABML consists of a generative model GH and a discriminative model DH, where DH learns labeled data in a supervised way and GH learns unlabeled data by synthesizing real images. We adopt an adversarial learning (AL) strategy to transfer the knowledge of unlabeled data to DH by making GH and DH mutually learn from each other. To solve the second problem, we propose a novel Weibull cross-entropy loss (WCE) by using the Weibull distribution, which can distinguish tiny differences of distances and explicitly force similar/dissimilar distances as small/large as possible. Thus, the learned features are more discriminative. Finally, by incorporating ABML with WCE loss, our model can acquire more semantic and discriminative features. Extensive experiments on four common data sets (CIFAR-10, large database of handwritten digits (MNIST), ImageNet-10, and NUS-WIDE) and a large-scale data set ImageNet demonstrate that our approach successfully overcomes the two difficulties above and significantly outperforms state-of-the-art hashing methods. |
关键词 | Data models Semantics Force Computational modeling Hash functions Binary codes Training data Adversarial learning (AL) deep learning hashing |
DOI | 10.1109/TNNLS.2021.3055834 |
关键词[WOS] | IMAGE RETRIEVAL |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[U1913601] ; National Natural Science Foundation of China[U20A20224] ; National Natural Science Foundation of China[61720106012] ; National Natural Science Foundation of China[62003343] ; National Natural Science Foundation of China[62073325] ; National Key Research and Development Program of China[2018YFC2001700] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDB32040000] ; Youth Innovation Promotion Association of the Chinese Academy of Sciences (CAS)[2020140] |
项目资助者 | National Natural Science Foundation of China ; National Key Research and Development Program of China ; Strategic Priority Research Program of Chinese Academy of Sciences ; Youth Innovation Promotion Association of the Chinese Academy of Sciences (CAS) |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000732400100001 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | AI芯片与智能计算 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/46837 |
专题 | 复杂系统认知与决策实验室_高效智能计算与学习 |
通讯作者 | Hou, Zeng-Guang |
作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 6.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China 7.Macau Univ Sci & Technol, Joint Lab Intelligence Sci & Technol, Inst Syst Engn, Macau 999078, 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, Guanan,Hu, Qinghao,Yang, Yang,et al. Adversarial Binary Mutual Learning for Semi-Supervised Deep Hashing[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021:15. |
APA | Wang, Guanan,Hu, Qinghao,Yang, Yang,Cheng, Jian,&Hou, Zeng-Guang.(2021).Adversarial Binary Mutual Learning for Semi-Supervised Deep Hashing.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,15. |
MLA | Wang, Guanan,et al."Adversarial Binary Mutual Learning for Semi-Supervised Deep Hashing".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021):15. |
条目包含的文件 | 条目无相关文件。 |
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