期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 58, 期 1, 页码 110-122出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2019.2933609
关键词
Hyperspectral imaging; Logic gates; Task analysis; Convolution; Support vector machines; Attention module; convolutional neural network (CNN); gating mechanism; hyperspectral image classification
类别
资金
- German Research Foundation (DFG) [ZH 498/7-2]
- European Research Council (ERC) under the European Union [ERC-2016StG-714087]
- Helmholtz Association [VH-NG-1018]
Over the past few years, hyperspectral image classification using convolutional neural networks (CNNs) has progressed significantly. In spite of their effectiveness, given that hyperspectral images are of high dimensionality, CNNs can be hindered by their modeling of all spectral bands with the same weight, as probably not all bands are equally informative and predictive. Moreover, the usage of useless spectral bands in CNNs may even introduce noises and weaken the performance of networks. For the sake of boosting the representational capacity of CNNs for spectral-spatial hyperspectral data classification, in this work, we improve networks by discriminating the significance of different spectral bands. We design a network unit, which is termed as the spectral attention module, that makes use of a gating mechanism to adaptively recalibrate spectral bands by selectively emphasizing informative bands and suppressing less useful ones. We theoretically analyze and discuss why such a spectral attention module helps in a CNN for hyperspectral image classification. We demonstrate using extensive experiments that in comparison with state-of-the-art approaches, the spectral attention module-based convolutional networks are able to offer competitive results. Furthermore, this work sheds light on how a CNN interacts with spectral bands for the purpose of 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