期刊
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
卷 18, 期 3, 页码 518-522出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2020.2979604
关键词
Training; Feature extraction; Iron; Hyperspectral imaging; Convolutional neural networks; Deep learning; Convolutional neural network (CNN); deep learning; hyperspectral image (HSI) classification; limited training samples; siamese network
类别
资金
- Natural Science Foundation of China [61971164]
- Open Fund of State Key Laboratory of Frozen Soil Engineering [SKLFSE201614]
In recent years, deep convolutional neural networks have been widely used for hyperspectral image classification, but the dependence on sufficient training samples is a challenge. The proposed Dual-SCNN method combines CNN, siamese network, and spectral-spatial feature fusion, and uses adversarial training and data augmentation to improve classification performance with limited training samples.
In recent years, deep convolutional neural networks (CNNs) have been widely used for hyperspectral image (HSI) classification. The powerful feature extraction capability and high classification performance of CNN highly depend on sufficient training samples. Unfortunately, it is not a common situation because collecting training samples is time-consuming and expensive. In this letter, in order to make the most of deep CNN with limited training samples, dual-path siamese CNN (Dual-SCNN) is proposed for HSI classification. Specifically, the proposed classification framework is a combination of extended morphological profiles, CNN, siamese network, and spectral-spatial feature fusion. In order to solve the problem of insufficiency in hard negative pairs during the training of a siamese network, adversarial training is combined with Dual-SCNN (Dual-SCNN-AT) for HSI classification. Moreover, a data augmentation method titled mixup is combined with Dual-SCNN and Dual-SCNN-AT to further improve the classification performance of HSI. The obtained results on widely used hyperspectral data sets reveal that the proposed methods provide the competitive results in terms of classification accuracy, especially with limited training 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