Self-Supervised Learning for Image Segmentation: A Comprehensive Survey

TL;DR

This survey reviews over 150 recent SSL-based image segmentation methods, categorizing tasks and datasets, and discusses future research directions to advance the field of self-supervised learning in computer vision.

Contribution

It provides a comprehensive categorization and analysis of SSL techniques for image segmentation, guiding future research and understanding of the field.

Findings

SSL effectively reduces reliance on labeled data for segmentation tasks

Pretext tasks and benchmark datasets are systematically categorized

Key challenges and future directions are identified

Abstract

Supervised learning demands large amounts of precisely annotated data to achieve promising results. Such data curation is labor-intensive and imposes significant overhead regarding time and costs. Self-supervised learning (SSL) partially overcomes these limitations by exploiting vast amounts of unlabeled data and creating surrogate (pretext or proxy) tasks to learn useful representations without manual labeling. As a result, SSL has become a powerful machine learning (ML) paradigm for solving several practical downstream computer vision problems, such as classification, detection, and segmentation. Image segmentation is the cornerstone of many high-level visual perception applications, including medical imaging, intelligent transportation, agriculture, and surveillance. Although there is substantial research potential for developing advanced algorithms for SSL-based semantic segmentation, a comprehensive study of existing methodologies is essential to trace advances and guide emerging researchers. This survey thoroughly investigates over 150 recent image segmentation articles, particularly focusing on SSL. It provides a practical categorization of pretext tasks, downstream tasks, and commonly used benchmark datasets for image segmentation research. It concludes with key observations distilled from a large body of literature and offers future directions to make this research field more accessible and comprehensible for readers.