期刊
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
卷 13, 期 -, 页码 5833-5846出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2020.3026316
关键词
Kernel; Hyperspectral imaging; Sun; Task analysis; Principal component analysis; Standards; Domain adaptation (DA); hyperspectral image (HSI) classification; ideal regularization (IR); multiple kernel learning (MKL); subspace alignment (SA)
类别
资金
- National High Technology Research and Development Program of China (863 Program) [2015AA7072012E]
- National Natural Science Foundation of China [61871177, 11771130, 41971296, 41671342]
- Zhejiang Provincial Natural Science Foundation of China [LR19D010001]
- State Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University [18R05]
- National Basic Research Program [JCKY2020110C]
- National Pre-Research Foundation [304020202]
This article proposes a novel unsupervised domain adaptation (DA) method called ideal regularized discriminative multiple kernel subspace alignment (IRDMKSA) for hyperspectral image (HSI) classification. The proposed IRDMKSA method includes three main steps: ideal regularization, discriminative multiple kernel learning, and subspace alignment. The ideal regularization strategy exploits label information of source domain to refine the standard source and target kernels and also to build a connection between them. The discriminative multiple kernel learning can learn a composite kernel to describe the nonlinearity of HSI samples by fusing complementary information among different single kernels. Finally, the subspace alignment is used to diminish the difference between source and target composite kernels. The proposed IRDMKSA method exploits both the sample similarity and label similarity and makes the resulting kernel more appropriate for DA tasks. Experimental results on four DA tasks show that the performance of IRDMKSA is better than some classical unsupervised DA methods for the HSI classification.
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