期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 57, 期 10, 页码 8065-8080出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2019.2918080
关键词
Deep learning (DL); feature extraction; hyper-spectral image (HSI) classification; residual neural networks; visual attention
类别
资金
- Ministerio de Educacion
- Junta de Extremadura [GR18060]
- European Union [734541]
- National Natural Science Foundation of China [61771496]
- Guangdong Provincial Natural Science Foundation [2016A030313254]
- National Key Research and Development Program of China [2017YFB0502900]
- Marie Curie Actions (MSCA) [734541] Funding Source: Marie Curie Actions (MSCA)
Deep neural networks (DNNs), including convolutional neural networks (CNNs) and residual networks (ResNets) models, are able to learn abstract representations from the input data by considering a deep hierarchy of layers that perform advanced feature extraction. The combination of these models with visual attention techniques can assist with the identification of the most representative parts of the data from a visual standpoint, obtained through more detailed filtering of the features extracted by the operational layers of the network. This is of significant interest for analyzing remotely sensed hyperspectral images (HSIs), characterized by their very high spectral dimensionality. However, few efforts have been conducted in the literature in order to adapt visual attention methods to remotely sensed HSI data analysis. In this paper, we introduce a new visual attention-driven technique for the HSI classification. Specifically, we incorporate attention mechanisms to a ResNet in order to better characterize the spectral-spatial information contained in the data. Our newly proposed method calculates a mask that is applied to the features obtained by the network in order to identify the most desirable ones for classification purposes. Our experiments, conducted using four widely used HSI data sets, reveal that the proposed deep attention model provides competitive advantages in terms of classification accuracy when compared to other state-of-the-art methods.
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