A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends

TL;DR

This survey comprehensively reviews self-supervised learning algorithms, their applications, key trends, and open research questions, highlighting its growing importance in learning from unlabeled data across various domains.

Contribution

It provides a detailed overview of SSL methods, compares their core principles, and discusses recent trends and open challenges in the field.

Findings

SSL algorithms are increasingly diverse and effective.

SSL has broad applications in vision and NLP.

Three main research trends are identified.

Abstract

Deep supervised learning algorithms typically require a large volume of labeled data to achieve satisfactory performance. However, the process of collecting and labeling such data can be expensive and time-consuming. Self-supervised learning (SSL), a subset of unsupervised learning, aims to learn discriminative features from unlabeled data without relying on human-annotated labels. SSL has garnered significant attention recently, leading to the development of numerous related algorithms. However, there is a dearth of comprehensive studies that elucidate the connections and evolution of different SSL variants. This paper presents a review of diverse SSL methods, encompassing algorithmic aspects, application domains, three key trends, and open research questions. Firstly, we provide a detailed introduction to the motivations behind most SSL algorithms and compare their commonalities and differences. Secondly, we explore representative applications of SSL in domains such as image processing, computer vision, and natural language processing. Lastly, we discuss the three primary trends observed in SSL research and highlight the open questions that remain. A curated collection of valuable resources can be accessed at https://github.com/guijiejie/SSL.