SPA: a graph spectral alignment perspective for domain adaptation
Unsupervised domain adaptation (UDA) is a pivotal form in machine learning to extend the
in-domain model to the distinctive target domains where the data distributions differ. Most …
in-domain model to the distinctive target domains where the data distributions differ. Most …
Improving Unsupervised Domain Adaptation: A Pseudo-candidate Set Approach
Unsupervised domain adaptation (UDA) is a critical challenge in machine learning, aiming
to transfer knowledge from a labeled source domain to an unlabeled target domain. In this …
to transfer knowledge from a labeled source domain to an unlabeled target domain. In this …
Learning invariant representation with consistency and diversity for semi-supervised source hypothesis transfer
Semi-supervised Domain adaptation (SSDA) has shown promising results by leveraging
unlabeled data and limited labeled samples in the target domain. However, accessibility to …
unlabeled data and limited labeled samples in the target domain. However, accessibility to …
Cross-Scene Classification of Remote Sensing Images Based on General-Specific Prototype Contrastive Learning
P Chen, Y Qiu, L Guo, X Zhang, F Liu… - IEEE Journal of …, 2024 - ieeexplore.ieee.org
In recent years, constrained by the challenges associated with expensive data annotation
and poor generalization ability in supervised models, domain adaptation has been …
and poor generalization ability in supervised models, domain adaptation has been …
Domain-invariant Label Propagation with Adaptive Graph Regularization
Y Zhang, J Tao, L Yan - IEEE Access, 2024 - ieeexplore.ieee.org
As an effective machine learning paradigm, domain adaptation (DA) learning aims to
enhance the learning performance of the target domain by utilizing other relevant but distinct …
enhance the learning performance of the target domain by utilizing other relevant but distinct …