Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification
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.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationDomain AdaptationMulti-Source Unsupervised Domain AdaptationPseudo LabelUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Tackling unsupervised multi-source domain adaptation with optimism and consistency
It has been known for a while that the problem of multi-source domain adaptation can be regarded as a single source domain adaptation task where the source domain corresponds to a mixture of the original source domains. …
Domain AdaptationOpen-Ended Question AnsweringMulti-Target Domain Adaptation with Collaborative Consistency Learning
Recently unsupervised domain adaptation for the semantic segmentation task has become more and more popular due to high-cost of pixel-level annotation on real-world images. However, most domain adaptation methods are onl…
Domain AdaptationMulti-target Domain AdaptationSemantic SegmentationUnsupervised Domain AdaptationConsistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation
Unsupervised domain adaptation for semantic segmentation has been intensively studied due to the low cost of the pixel-level annotation for synthetic data. The most common approaches try to generate images or features mi…
Domain AdaptationSemantic SegmentationStyle TransferUnsupervised Domain AdaptationMulti-Source domain adaptation via supervised contrastive learning and confident consistency regularization
Multi-Source Unsupervised Domain Adaptation (multi-source UDA) aims to learn a model from several labeled source domains while performing well on a different target domain where only unlabeled data are available at train…
Contrastive LearningDomain AdaptationMulti-Source Unsupervised Domain AdaptationUnsupervised Domain AdaptationUnsupervised Domain Adaptive Fundus Image Segmentation with Category-level Regularization
Existing unsupervised domain adaptation methods based on adversarial learning have achieved good performance in several medical imaging tasks. However, these methods focus only on global distribution adaptation and ignor…
Domain AdaptationImage SegmentationSemantic SegmentationUnsupervised Domain Adaptation