Domain Adaptation Through Transferring both the Source-Knowledge and Target-Relatedness Simultaneously

by   Qing Tian, et al.

Domain adaptation (DA) is an emerging research topic in the field of machine learning and pattern recognition, which aims to assist the learning of target domains by transferring model knowledge from the source domains. To perform DA, a variety of methods have been proposed, most of which concentrate on the scenario of single source and single target domain (1S1T). However, in real applications, usually multiple domains, especially target domains, are involved, which cannot be handled directly by those 1S1T models. Although related works on multi-target domains have been proposed, they are quite rare, and more unfortunately, nearly none of them model the source domain knowledge and leverage the target-relatedness jointly. To overcome these shortcomings, in this paper we propose a kind of DA model through TrAnsferring both the source-KnowlEdge and TargEt-Relatedness, DATAKETER for short. In this way, not only the supervision knowledge from the source domain, but also the potential relatedness among the target domains are simultaneously modeled for exploitation in the process of 1SmT DA. In addition, we construct an alternating optimization algorithm to solve the variables of the proposed model with convergence guarantee. Finally, through extensive experiments on both benchmark and real datasets, we validate the effectiveness and superiority of the proposed method.


page 3

page 9

page 12


Unsupervised Domain Adaptation Through Transferring both the Source-Knowledge and Target-Relatedness Simultaneously

Unsupervised domain adaptation (UDA) is an emerging research topic in th...

Unsupervised Multi-Target Domain Adaptation for Acoustic Scene Classification

It is well known that the mismatch between training (source) and test (t...

Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling

Domain adaptation (DA) aims to transfer knowledge learned from a labeled...

AD-CLIP: Adapting Domains in Prompt Space Using CLIP

Although deep learning models have shown impressive performance on super...

Regressive Domain Adaptation for Unsupervised Keypoint Detection

Domain adaptation (DA) aims at transferring knowledge from a labeled sou...

Domain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation

Domain Adaptation (DA) has the potential to greatly help the generalizat...

Visualizing Transferred Knowledge: An Interpretive Model of Unsupervised Domain Adaptation

Many research efforts have been committed to unsupervised domain adaptat...

Please sign up or login with your details

Forgot password? Click here to reset