Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey
It addresses the time-consuming and laborious labeling process in computer vision for researchers and practitioners, but it is incremental as a review paper.
This survey tackles the problem of reducing labeling effort in semantic segmentation by reviewing pseudo-label methods for semi-supervised learning, categorizing state-of-the-art results and exploring applications in medical and remote-sensing images.
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.