Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well
on another set of data (target domain), which is different but has similar properties as the …

This article takes a problem-oriented perspective and presents a comprehensive review of
transfer-learning methods, both shallow and deep, for cross-dataset visual recognition …

When the training and the test data belong to different domains, the accuracy of an object
classifier is significantly reduced. Therefore, several algorithms have been proposed in the …

Transfer learning has achieved promising results by leveraging knowledge from the source
domain to annotate the target domain which has few or none labels. Existing methods often …

In domain adaptation, maximum mean discrepancy (MMD) has been widely adopted as a
discrepancy metric between the distributions of source and target domains. However …

Reducing the feature distribution shift caused by the factor of visual-environment changes,
named visual-environment changes (VE-changes), is a hot issue in domain adaptation …

Abstract Domain adaptation deals with training models using large scale labeled data from a
specific source domain and then adapting the knowledge to certain target domains that have …

To bridge source and target domains for domain adaptation, there are three important types
of information including data structure, domain label, and class label. Most existing domain …

Unsupervised domain adaptation has caught appealing attentions as it facilitates the
unlabeled target learning by borrowing existing well-established source domain knowledge …

Subspace learning and reconstruction have been widely explored in recent transfer learning
work. Generally, a specially designed projection and reconstruction transfer functions …