Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey

TL;DR

This survey reviews semi-supervised semantic segmentation methods using pseudo-labels, highlighting their applications in medical and remote sensing images, and discusses future research directions.

Contribution

It provides the first comprehensive overview of pseudo-label techniques in semi-supervised semantic segmentation, categorizing methods and exploring diverse application areas.

Findings

Categorized pseudo-label methods for semantic segmentation

Applied pseudo-label techniques to medical imaging

Extended pseudo-label methods to remote sensing images

Abstract

Semantic segmentation is an important and popular research area in computer vision that focuses on classifying pixels in an image based on their semantics. However, supervised deep learning requires large amounts of data to train models and the process of labeling images pixel by pixel is time-consuming and laborious. This review aims to provide a first comprehensive and organized overview of the state-of-the-art research results on pseudo-label methods in the field of semi-supervised semantic segmentation, which we categorize from different perspectives and present specific methods for specific application areas. In addition, we explore the application of pseudo-label technology in medical and remote-sensing image segmentation. Finally, we also propose some feasible future research directions to address the existing challenges.