Deep transfer learning (DTL), which incorporates new ideas from deep neural networks into
transfer learning (TL), has achieved excellent success in computer vision, text classification …

Abstract Domain adaptation (DA) aims to transfer the knowledge learned from source
domain to an unlabeled target domain. Some recent works tackle source-free domain …

Abstract Unsupervised Domain Adaptation solves knowledge transfer along with the
coexistence of well-annotated source domain and unlabeled target instances. However, the …

We investigate a practical domain adaptation task, called source-free domain adaptation
(SFUDA), where the source pretrained model is adapted to the target domain without access …

Conventional machine learning relies on two presumptions:(1) the training and testing
datasets follow the same independent distribution, and (2) an adequate quantity of samples …

We study a practical domain adaptation task, called source-free unsupervised domain
adaptation (UDA) problem, in which we cannot access source domain data due to data …

As a key component widely used in electric multiple units (EMU), fault diagnosis of EMU
bearing is an important link. Typically, labeled data from different conditions provides the …

Unsupervised domain adaptation (UDA) aims to utilize knowledge from a label-rich source
domain to understand a similar yet distinct unlabeled target domain. Notably, global …

Due to privacy concerns and data transmission issues, Source-free Unsupervised Domain
Adaptation (SFDA) has gained popularity. It exploits pre-trained source models, rather than …

Unsupervised domain adaptation (UDA) aims to transfer the knowledge learned from a
labeled source domain to an unlabeled target domain. Existing UDA methods require …