Rotation-Invariant Attention Network for Hyperspectral Image Classification
文献类型:期刊论文
作者 | Zheng, Xiangtao3; Sun, Hao2,3; Lu, Xiaoqiang3; Xie, Wei1 |
刊名 | IEEE Transactions on Image Processing |
出版日期 | 2022 |
卷号 | 31页码:4251-4265 |
ISSN号 | 10577149;19410042 |
关键词 | Hyperspectral image classification convolutional neural network rotation-invariant network spectralspatial feature extraction attention mechanism |
DOI | 10.1109/TIP.2022.3177322 |
产权排序 | 1 |
英文摘要 | Hyperspectral image (HSI) classification refers to identifying land-cover categories of pixels based on spectral signatures and spatial information of HSIs. In recent deep learning-based methods, to explore the spatial information of HSIs, the HSI patch is usually cropped from original HSI as the input. And 3 × 3 convolution is utilized as a key component to capture spatial features for HSI classification. However, the 3 × 3 convolution is sensitive to the spatial rotation of inputs, which results in that recent methods perform worse in rotated HSIs. To alleviate this problem, a rotation-invariant attention network (RIAN) is proposed for HSI classification. First, a center spectral attention (CSpeA) module is designed to avoid the influence of other categories of pixels to suppress redundant spectral bands. Then, a rectified spatial attention (RSpaA) module is proposed to replace 3 × 3 convolution for extracting rotation-invariant spectral-spatial features from HSI patches. The CSpeA module, the 1 × 1 convolution and the RSpaA module are utilized to build the proposed RIAN for HSI classification. Experimental results demonstrate that RIAN is invariant to the spatial rotation of HSIs and has superior performance, e.g., achieving an overall accuracy of 86.53% (1.04% improvement) on the Houston database. The codes of this work are available at https://github.com/spectralpublic/RIAN. © 1992-2012 IEEE. |
语种 | 英语 |
出版者 | Institute of Electrical and Electronics Engineers Inc. |
WOS记录号 | WOS:000818885700004 |
源URL | [http://ir.opt.ac.cn/handle/181661/96025] |
专题 | 西安光学精密机械研究所_光学影像学习与分析中心 |
通讯作者 | Lu, Xiaoqiang |
作者单位 | 1.Central China Normal University, Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, National Language Resources Monitoring and Research Center for Network Media, School of Computer, Wuhan; 430079, China 2.University of Chinese Academy of Sciences, Beijing; 100049, China; 3.Xi'An Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Key Laboratory of Spectral Imaging Technology CAS, Xi'an; 710119, China; |
推荐引用方式 GB/T 7714 | Zheng, Xiangtao,Sun, Hao,Lu, Xiaoqiang,et al. Rotation-Invariant Attention Network for Hyperspectral Image Classification[J]. IEEE Transactions on Image Processing,2022,31:4251-4265. |
APA | Zheng, Xiangtao,Sun, Hao,Lu, Xiaoqiang,&Xie, Wei.(2022).Rotation-Invariant Attention Network for Hyperspectral Image Classification.IEEE Transactions on Image Processing,31,4251-4265. |
MLA | Zheng, Xiangtao,et al."Rotation-Invariant Attention Network for Hyperspectral Image Classification".IEEE Transactions on Image Processing 31(2022):4251-4265. |
入库方式: OAI收割
来源:西安光学精密机械研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。