期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 59, 期 9, 页码 7758-7772出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2020.3034133
关键词
Training; Support vector machines; Radio frequency; Deep learning; Task analysis; Unsupervised learning; Residual neural networks; Deep learning; hyperspectral image (HSI) classification; multiview learning; small samples
类别
资金
- National Natural Science Foundation of China [41201477]
This article proposes a deep multiview learning method to address the small sample problem in hyperspectral image classification. By constructing multiple views and designing a deep residual network, the method improves classification accuracy in an unsupervised learning setting.
Recently, the field of hyperspectral image (HSI) classification is dominated by deep learning-based methods. However, training deep learning models usually needs a large number of labeled samples to optimize thousands of parameters. In this article, a deep multiview learning method is proposed to deal with the small sample problem of HSI. First, two views of an HSI scene are constructed by applying principal component analysis to different bands. Second, a deep residual network is designed to embed the different views of a sample to a latent space. The designed deep residual network is trained by maximizing agreement between differently augmented views of the same data sample via a contrastive loss in the latent space. Note that the training procedure of the designed deep residual network does not use labeled information. Therefore, the proposed method belongs to the category of unsupervised learning, which could alleviate the lack of labeled training samples. Finally, a conventional machine learning method (e.g., support vector machine) is used to complete the classification task in the learned latent space. To demonstrate the effectiveness of the proposed method, extensive experiments are carried on four widely used hyperspectral data sets. The experimental results demonstrate that the proposed method could improve the classification accuracy with small samples.
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