Domain consistency regularization for unsupervised multi-source domain adaptive classification. (December 2022)

• Record Type: Journal Article
• Authors: Luo, Zhipeng; Zhang, Xiaobing; Lu, Shijian; Yi, Shuai
• Is Part Of: Pattern recognition. Volume 132(2022)
• Publication Date: 2022-12
• Subjects: Domain adaptation -- Transfer learning -- Adversarial learning -- Feature alignment; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.108955
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose a novel multi-source domain adaptation method for classification. We leverage domain consistency regularization for effective feature alignment. An adaptive weighting strategy is designed to tackle negative transfer. The proposed method achieves state-of-the-art performance on multiple benchmarks. Abstract: Deep learning-based multi-source unsupervised domain adaptation (MUDA) has been actively studied in recent years. Compared with single-source unsupervised domain adaptation (SUDA), domain shift in MUDA exists not only between the source and target domains but also among multiple source domains. Most existing MUDA algorithms focus on extracting domain-invariant representations among all domains whereas the task-specific decision boundaries among classes are largely neglected. In this paper, we propose an end-to-end trainable network that exploits domain Consistency Regularization for unsupervised Multi-source domain Adaptive classification (CRMA). CRMA aligns not only the distributions of each pair of source and target domains but also that of all domains. For each pair of source and target domains, we employ an intra-domain consistency to regularize a pair of domain-specific classifiers to achieve intra-domain alignment . In addition, we design an inter-domain consistency that targets joint inter-domain alignment among all domains. To address different similarities between multiple source domains and the target domain, we design an authorization strategy that assigns different authorities to domain-specific classifiers adaptively for optimal pseudo label prediction and self-training. Extensive experiments show that CRMA tackles unsupervised domain adaptation effectively under a multi-source setup and achieves superior adaptation consistently across multiple MUDA datasets.