Self-supervised image clustering from multiple incomplete views via constrastive complementary generation

doi:10.1049/cvi2.12147

	Self-supervised image clustering from multiple incomplete views via constrastive complementary generation
	Wang, Jiatai 1; Xu, Zhiwei 1,2; Yang, Xuewen 3; Guo, Dongjin 1; Liu, Limin 1
	2022-10-10
发表期刊	IET COMPUTER VISION
ISSN	1751-9632
页码	14
摘要	Incomplete Multi-View Clustering aims to enhance clustering performance by using data from multiple modalities. Despite the fact that several approaches for studying this issue have been proposed, the following drawbacks still persist: (1) It is difficult to learn latent representations that account for complementarity yet consistency without using label information; (2) and thus fails to take full advantage of the hidden information in incomplete data results in suboptimal clustering performance when complete data is scarce. In this study, Contrastive Incomplete Multi-View Image Clustering with Generative Adversarial Networks (CIMIC-GAN), which uses Generative Adversarial Network (GAN) to fill in incomplete data and uses double contrastive learning to learn consistency on complete and incomplete data is proposed. More specifically, considering diversity and complementary information among multiple modalities, we incorporate autoencoding representation of complete and incomplete data into double contrastive learning to achieve learning consistency. Integrating GANs into the autoencoding process can not only take full advantage of new features of incomplete data, but also better generalise the model in the presence of high data missing rates. Experiments conducted on four extensively used data sets show that CIMIC-GAN outperforms state-of-the-art incomplete multi-View clustering methods.
关键词	clustering from multiple incomplete views computer vision constrastive learning generative adversarial network
DOI	10.1049/cvi2.12147
收录类别	SCI
语种	英语
资助项目	Science and Technology Planning Project of Inner Mongolia Autonomous Region[2019GG372] ; National Science Foundation of China[61962045] ; National Science Foundation of China[62062055] ; National Science Foundation of China[61650205] ; National Science Foundation of China[61902382] ; National Science Foundation of China[61972381] ; Open Foundation of Inner Mongolia Key Laboratory of Discipline Inspection and Supervision[IMDBD2020017] ; Open Foundation of Inner Mongolia Key Laboratory of Discipline Inspection and Supervision[IMDBD2020018]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000865457600001
出版者	WILEY
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19797
专题	中国科学院计算技术研究所期刊论文
通讯作者	Xu, Zhiwei
作者单位	1.Inner Mongolia Univ Technol, Coll Data Sci & Applicat, Hohhot 010080, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 3.InnoPeak Technol Inc, Palo Alto, CA USA
推荐引用方式 GB/T 7714	Wang, Jiatai,Xu, Zhiwei,Yang, Xuewen,et al. Self-supervised image clustering from multiple incomplete views via constrastive complementary generation[J]. IET COMPUTER VISION,2022:14.
APA	Wang, Jiatai,Xu, Zhiwei,Yang, Xuewen,Guo, Dongjin,&Liu, Limin.(2022).Self-supervised image clustering from multiple incomplete views via constrastive complementary generation.IET COMPUTER VISION,14.
MLA	Wang, Jiatai,et al."Self-supervised image clustering from multiple incomplete views via constrastive complementary generation".IET COMPUTER VISION (2022):14.