DeepAI AI Chat
Log In Sign Up

Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation

by   Antoine Saporta, et al.

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.


page 1

page 8


Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation

Unsupervised Domain Adaptation (UDA) is a transfer learning task which a...

Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation

Unsupervised domain adaptation (UDA) for semantic segmentation has been ...

Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation

Deep neural networks are typically trained in a single shot for a specif...

CD-TTA: Compound Domain Test-time Adaptation for Semantic Segmentation

Test-time adaptation (TTA) has attracted significant attention due to it...

Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation

Recent researches on unsupervised domain adaptation (UDA) have demonstra...

Exploiting Diverse Characteristics and Adversarial Ambivalence for Domain Adaptive Segmentation

Adapting semantic segmentation models to new domains is an important but...