Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation
This addresses the challenge of training a single model for real-world autonomous systems that must handle multiple domains, though it is incremental in adapting existing adversarial methods to a multi-target setup.
The paper tackles unsupervised domain adaptation for semantic segmentation across multiple target domains by introducing two adversarial frameworks, achieving consistent outperformance over baselines on newly-proposed benchmarks.
In this work, we address the task of unsupervised domain adaptation (UDA) for semantic segmentation in presence of multiple target domains: The objective is to train a single model that can handle all these domains at test time. Such a multi-target adaptation is crucial for a variety of scenarios that real-world autonomous systems must handle. It is a challenging setup since one faces not only the domain gap between the labeled source set and the unlabeled target set, but also the distribution shifts existing within the latter among the different target domains. To this end, we introduce two adversarial frameworks: (i) multi-discriminator, which explicitly aligns each target domain to its counterparts, and (ii) multi-target knowledge transfer, which learns a target-agnostic model thanks to a multi-teacher/single-student distillation mechanism.The evaluation is done on four newly-proposed multi-target benchmarks for UDA in semantic segmentation. In all tested scenarios, our approaches consistently outperform baselines, setting competitive standards for the novel task.