Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey
It provides a comprehensive reference for researchers in academia and industry to understand and advance methods for adapting semantic segmentation models across domains, which is critical for applications like autonomous driving and medical imaging.
This survey summarizes five years of research on unsupervised domain adaptation for semantic image segmentation, addressing the high cost of annotated data by leveraging cheaper unlabeled data to adapt models to new environments.
Semantic segmentation plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. Yet, the state-of-the-art models rely on large amount of annotated samples, which are more expensive to obtain than in tasks such as image classification. Since unlabelled data is instead significantly cheaper to obtain, it is not surprising that Unsupervised Domain Adaptation reached a broad success within the semantic segmentation community. This survey is an effort to summarize five years of this incredibly rapidly growing field, which embraces the importance of semantic segmentation itself and a critical need of adapting segmentation models to new environments. We present the most important semantic segmentation methods; we provide a comprehensive survey on domain adaptation techniques for semantic segmentation; we unveil newer trends such as multi-domain learning, domain generalization, test-time adaptation or source-free domain adaptation; we conclude this survey by describing datasets and benchmarks most widely used in semantic segmentation research. We hope that this survey will provide researchers across academia and industry with a comprehensive reference guide and will help them in fostering new research directions in the field.