Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation

TL;DR

This paper introduces a novel domain adaptation framework for semantic segmentation that uses learnable clustering and alignment techniques to better handle multi-modal data distributions across domains, improving performance over existing methods.

Contribution

The paper proposes a cross-domain grouping and alignment framework with a learnable clustering module and new loss functions to enhance domain adaptation in semantic segmentation.

Findings

Outperforms state-of-the-art methods on various domain adaptation benchmarks.

Effectively handles multi-modal data distributions across domains.

Addresses class imbalance issues in domain adaptation.

Abstract

Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) deal with all the samples from the two domains in a global or category-aware manner. They do not consider an inter-class variation within the target domain itself or estimated category, providing the limitation to encode the domains having a multi-modal data distribution. To overcome this limitation, we introduce a learnable clustering module, and a novel domain adaptation framework called cross-domain grouping and alignment. To cluster the samples across domains with an aim to maximize the domain alignment without forgetting precise segmentation ability on the source domain, we present two loss functions, in particular, for encouraging semantic consistency and orthogonality among the clusters. We also present a loss so as to solve a class imbalance problem, which is the other limitation of the previous methods. Our experiments show that our method consistently boosts the adaptation performance in semantic segmentation, outperforming the state-of-the-arts on various domain adaptation settings.