Self-supervised Multi-view Clustering in Computer Vision: A Survey

TL;DR

This survey reviews the recent progress of self-supervised multi-view clustering in computer vision, highlighting its advantages, methodologies, datasets, and open challenges in the evolving field.

Contribution

It provides a comprehensive analysis and classification of current self-supervised MVC methods, datasets, and challenges, filling a gap in existing literature.

Findings

Self-supervised MVC leverages proxy tasks for representation learning.

The survey categorizes methods and discusses their applications.

Open problems for future research are identified.

Abstract

Multi-view clustering (MVC) has had significant implications in cross-modal representation learning and data-driven decision-making in recent years. It accomplishes this by leveraging the consistency and complementary information among multiple views to cluster samples into distinct groups. However, as contrastive learning continues to evolve within the field of computer vision, self-supervised learning has also made substantial research progress and is progressively becoming dominant in MVC methods. It guides the clustering process by designing proxy tasks to mine the representation of image and video data itself as supervisory information. Despite the rapid development of self-supervised MVC, there has yet to be a comprehensive survey to analyze and summarize the current state of research progress. Therefore, this paper explores the reasons and advantages of the emergence of self-supervised MVC and discusses the internal connections and classifications of common datasets, data issues, representation learning methods, and self-supervised learning methods. This paper does not only introduce the mechanisms for each category of methods but also gives a few examples of how these techniques are used. In the end, some open problems are pointed out for further investigation and development.