期刊
KNOWLEDGE-BASED SYSTEMS
卷 205, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.knosys.2020.106285
关键词
Subspace learning; Self-paced learning; Unsupervised domain adaptation
资金
- Department of Education of Guangdong Province, China [2018KQNCX075]
- City University of Hong Kong [7004884, 7005055]
- Natural Science Foundation of Guangdong Province, China [2019A1515010943]
- Key Project of Basic and Applied Basic Research of Colleges and Universities in Guangdong Province, China (Natural Science) [2018KZDXM035]
- Basic and Applied Basic Research of Colleges and Universities in Guangdong Province, China (Special Projects in Artificial Intelligence) [2019KZDZX1030]
- Li Ka Shing Foundation, China Cross-Disciplinary Research Grant [2020LKSFG04D]
Unsupervised domain adaptation aims to address the problem in which the source data and target data are related but distributed differently. A widely-used two-stage strategy is to learn a domain-invariant subspace, and then train a cross-domain classifier on the resulting subspace. In this paper, we propose a single-stage domain adaption approach for joint subspace learning and discriminative learning. Specifically, a domain-invariant subspace and a cross-domain classifier are progressively learnt in a self-paced learning fashion. To avoid unlabeled target data dominating the overall loss and misleading model training, we progressively include more target data from easy to complex to optimize our model. Specifically, we propose an alternative optimization algorithm to efficiently find a reasonable solution for our task. Extensive experiments are conducted on multiple standard benchmarks to verify the effectiveness of the proposed approach. The results demonstrate that our model can outperform state-of-the-art non-deep domain adaptation methods. (C) 2020 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据