Publication Type

Journal Article

Version

acceptedVersion

Publication Date

5-2023

Abstract

Domain adaptation enables generalized learning in new environments by transferring knowledge from label-rich source domains to label-scarce target domains. As a more realistic extension, partial domain adaptation (PDA) relaxes the assumption of fully shared label space, and instead deals with the scenario where the target label space is a subset of the source label space. In this paper, we propose a Reinforced Adaptation Network (RAN) to address the challenging PDA problem. Specifically, a deep reinforcement learning model is proposed to learn source data selection policies. Meanwhile, a domain adaptation model is presented to simultaneously determine rewards and learn domain-invariant feature representations. By combining reinforcement learning and domain adaptation techniques, the proposed network alleviates negative transfer by automatically filtering out less relevant source data and promotes positive transfer by minimizing the distribution discrepancy across domains. Experiments on three benchmark datasets demonstrate that RAN consistently outperforms seventeen existing state-of-the-art methods by a large margin.

Keywords

Adaptation models, Reinforcement learning, Knowledge transfer, Training, Data models, Task analysis, Minimization, Deep reinforcement learning, partial domain adaptation, domain adaptation, transfer learning

Discipline

Databases and Information Systems | OS and Networks

Research Areas

Intelligent Systems and Optimization

Publication

IEEE Transactions on Circuits and Systems for Video Technology

Volume

33

Issue

5

First Page

2370

Last Page

2380

ISSN

1051-8215

Identifier

10.1109/TCSVT.2022.3223950

Publisher

Institute of Electrical and Electronics Engineers

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/TCSVT.2022.3223950

Download

Share

COinS