Unsupervised Domain Adaptation in Semantic Segmentation: a Review

TL;DR

This review paper comprehensively surveys recent methods in Unsupervised Domain Adaptation for semantic segmentation, categorizing approaches, discussing levels of adaptation, and comparing performance in autonomous driving scenarios.

Contribution

It provides a detailed categorization and overview of UDA techniques for semantic segmentation, highlighting recent advancements and open research directions.

Findings

Adversarial learning and generative methods are prominent in UDA.

Different adaptation levels include input, feature, and output.

Performance varies across methods in autonomous driving tasks.

Abstract

The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation. This task is attracting a wide interest, since semantic segmentation models require a huge amount of labeled data and the lack of data fitting specific requirements is the main limitation in the deployment of these techniques. This problem has been recently explored and has rapidly grown with a large number of ad-hoc approaches. This motivates us to build a comprehensive overview of the proposed methodologies and to provide a clear categorization. In this paper, we start by introducing the problem, its formulation and the various scenarios that can be considered. Then, we introduce the different levels at which adaptation strategies may be applied: namely, at the input (image) level, at the internal features representation and at the output level. Furthermore, we present a detailed overview of the literature in the field, dividing previous methods based on the following (non mutually exclusive) categories: adversarial learning, generative-based, analysis of the classifier discrepancies, self-teaching, entropy minimization, curriculum learning and multi-task learning. Novel research directions are also briefly introduced to give a hint of interesting open problems in the field. Finally, a comparison of the performance of the various methods in the widely used autonomous driving scenario is presented.