Adversarial Binary Mutual Learning for Semi-Supervised Deep Hashing

doi:10.1109/TNNLS.2021.3055834

	Adversarial Binary Mutual Learning for Semi-Supervised Deep Hashing
	Wang, Guanan 1,4; Hu, Qinghao 5; Yang, Yang 5; Cheng, Jian 5; Hou, Zeng-Guang 2,3,6,7
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2021-03-06
页码	15
关键词	Data models Semantics Force Computational modeling Hash functions Binary codes Training data Adversarial learning (AL) deep learning hashing
ISSN号	2162-237X
DOI	10.1109/TNNLS.2021.3055834
通讯作者	Hou, Zeng-Guang(zengguang.hou@ia.ac.cn)
英文摘要	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.
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]
WOS关键词	IMAGE RETRIEVAL
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000732400100001
资助机构	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)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/46836]
专题	类脑芯片与系统研究
通讯作者	Hou, Zeng-Guang
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Macau Univ Sci & Technol, Joint Lab Intelligence Sci & Technol, Inst Syst Engn, Macau 999078, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 5.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 6.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 7.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China
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.