Universal Multi-Source Domain Adaptation
Unsupervised domain adaptation enables intelligent models to transfer knowledge from a labeled source domain to a similar but unlabeled target domain. Recent study reveals that knowledge can be transferred from one source domain to another unknown target domain, called Universal Domain Adaptation (UDA). However, in the real-world application, there are often more than one source domain to be exploited for domain adaptation. In this paper, we formally propose a more general domain adaptation setting, universal multi-source domain adaptation (UMDA), where the label sets of multiple source domains can be different and the label set of target domain is completely unknown. The main challenges in UMDA are to identify the common label set between each source domain and target domain, and to keep the model scalable as the number of source domains increases. To address these challenges, we propose a universal multi-source adaptation network (UMAN) to solve the domain adaptation problem without increasing the complexity of the model in various UMDA settings. In UMAN, we estimate the reliability of each known class in the common label set via the prediction margin, which helps adversarial training to better align the distributions of multiple source domains and target domain in the common label set. Moreover, the theoretical guarantee for UMAN is also provided. Massive experimental results show that existing UDA and multi-source DA (MDA) methods cannot be directly applied to UMDA and the proposed UMAN achieves the state-of-the-art performance in various UMDA settings.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationUniversal Domain AdaptationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
DaSeGAN: Domain Adaptation for Segmentation Tasks via Generative Adversarial Networks
A weakness of deep learning methods is that they can fail when there is a mismatch between source and target data domains. In medical image applications, this is a common situation when data from new vendor devices or di…
Domain AdaptationDomain GeneralizationImage SegmentationMulti-Source Unsupervised Domain Adaptation+2Universal Domain Adaptation for Remote Sensing Image Scene Classification
The domain adaptation (DA) approaches available to date are usually not well suited for practical DA scenarios of remote sensing image classification, since these methods (such as unsupervised DA) rely on rich prior know…
ClassificationDomain Adaptationimage-classificationImage Classification+3Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias
Domain adaptation is a critical task in machine learning that aims to improve model performance on a target domain by leveraging knowledge from a related source domain. In this work, we introduce Universal Semi-Supervise…
Domain AdaptationPseudo LabelSemi-supervised Domain AdaptationUniversal Domain AdaptationUniversal Domain Adaptation
Domain adaptation aims to transfer knowledge in the presence of the domain gap. Existing domain adaptation methods rely on rich prior knowledge about the relationship between the label sets of source and target domains, …
Domain AdaptationUniversal Domain AdaptationGMM-COMET: Continual Source-Free Universal Domain Adaptation via a Mean Teacher and Gaussian Mixture Model-Based Pseudo-Labeling
Unsupervised domain adaptation tackles the problem that domain shifts between training and test data impair the performance of neural networks in many real-world applications. Thereby, in realistic scenarios, the source …
Unsupervised Domain AdaptationUniversal Domain Adaptation