Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey

TL;DR

This comprehensive survey reviews five years of unsupervised domain adaptation techniques for semantic image segmentation, highlighting key methods, trends, datasets, and benchmarks to guide future research in adapting models to new environments.

Contribution

It provides an extensive overview of recent advances, including emerging trends like multi-domain learning and source-free adaptation, serving as a valuable reference for researchers.

Findings

Summarizes state-of-the-art domain adaptation methods

Highlights new trends such as test-time adaptation

Provides a comprehensive list of datasets and benchmarks

Abstract

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.