Self-supervised multi-view clustering in computer vision: A survey

doi:10.1049/cvi2.12299

	Self-supervised multi-view clustering in computer vision: A survey
	Wang, Jiatai 1,2; Xu, Zhiwei 3,4; Yang, Xuewen 5; Li, Hailong 1; Li, Bo 1; Meng, Xuying 4
	2024-07-02
发表期刊	IET COMPUTER VISION
ISSN	1751-9632
页码	26
摘要	In recent years, multi-view clustering (MVC) has had significant implications in the fields of cross-modal representation learning and data-driven decision-making. Its main objective is to cluster samples into distinct groups by leveraging consistency and complementary information among multiple views. However, the field of computer vision has witnessed the evolution of contrastive learning, and self-supervised learning has made substantial research progress. Consequently, self-supervised learning is progressively becoming dominant in MVC methods. It involves designing proxy tasks to extract supervisory information from image and video data, thereby guiding the clustering process. Despite the rapid development of self-supervised MVC, there is currently no comprehensive survey analysing and summarising the current state of research progress. Hence, the authors aim to explore the emergence of self-supervised MVC by discussing the reasons and advantages behind it. Additionally, the internal connections and classifications of common datasets, data issues, representation learning methods, and self-supervised learning methods are investigated. The authors not only introduce the mechanisms for each category of methods, but also provide illustrative examples of their applications. Finally, some open problems are identified for further investigation and development. The self-supervised learning problem presents a significant challenge within the realm of MVC, and its investigation holds paramount importance for practical applications. The authors include commonly employed self-supervised MVC datasets and related problems, offering insights from both image and video perspectives. Subsequently, a novel classification method is aimed at categorising existing self-supervised MVC methods. Finally, it is imperative to highlight several open and challenging problems, encouraging researchers to delve deeper into further research and make substantial progress in this domain. image
关键词	computer vision pattern clustering
DOI	10.1049/cvi2.12299
收录类别	SCI
语种	英语
资助项目	National Science Foundation of China[61962045] ; National Science Foundation of China[62062055] ; National Science Foundation of China[61902382] ; National Science Foundation of China[61972381] ; Science and Technology Planning Project of Inner Mongolia Autonomous Region[2023YFSH0066] ; Program for Young Talents of Science and Technology in Universities of Inner Mongolia Autonomous Region[NJYT23104]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001260206100001
出版者	WILEY
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39877
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Xu, Zhiwei
作者单位	1.Inner Mongolia Univ Technol, Coll Data Sci & Applicat, Hohhot, Peoples R China 2.OPPO Res Inst, Audio Semant Res Dept, Beijing, Peoples R China 3.Haihe Lab ITAI, Tianjin, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 5.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 multi-view clustering in computer vision: A survey[J]. IET COMPUTER VISION,2024:26.
APA	Wang, Jiatai,Xu, Zhiwei,Yang, Xuewen,Li, Hailong,Li, Bo,&Meng, Xuying.(2024).Self-supervised multi-view clustering in computer vision: A survey.IET COMPUTER VISION,26.
MLA	Wang, Jiatai,et al."Self-supervised multi-view clustering in computer vision: A survey".IET COMPUTER VISION (2024):26.