IIDM: Inter and Intra-domain Mixing for Semi-supervised Domain Adaptation in Semantic Segmentation

TL;DR

This paper introduces IIDM, a semi-supervised domain adaptation framework for semantic segmentation that leverages inter- and intra-domain mixing to improve domain-invariant feature learning, outperforming previous methods.

Contribution

The paper proposes a novel IIDM framework that exploits both inter- and intra-domain mixing strategies to enhance semi-supervised domain adaptation in semantic segmentation.

Findings

IIDM surpasses previous methods on GTA5 to Cityscapes and SYNTHIA to Cityscapes benchmarks.

Intra-domain mixing enriches target domain information and improves feature invariance.

Inter-domain mixing reduces the domain gap effectively.

Abstract

Despite recent advances in semantic segmentation, an inevitable challenge is the performance degradation caused by the domain shift in real applications. Current dominant approach to solve this problem is unsupervised domain adaptation (UDA). However, the absence of labeled target data in UDA is overly restrictive and limits performance. To overcome this limitation, a more practical scenario called semi-supervised domain adaptation (SSDA) has been proposed. Existing SSDA methods are derived from the UDA paradigm and primarily focus on leveraging the unlabeled target data and source data. In this paper, we highlight the significance of exploiting the intra-domain information between the labeled target data and unlabeled target data. Instead of solely using the scarce labeled target data for supervision, we propose a novel SSDA framework that incorporates both Inter and Intra Domain Mixing (IIDM), where inter-domain mixing mitigates the source-target domain gap and intra-domain mixing enriches the available target domain information, and the network can capture more domain-invariant features. We also explore different domain mixing strategies to better exploit the target domain information. Comprehensive experiments conducted on the GTA5 to Cityscapes and SYNTHIA to Cityscapes benchmarks demonstrate the effectiveness of IIDM, surpassing previous methods by a large margin.