• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Wu, Chunran (Wu, Chunran.) | Tong, Lei (Tong, Lei.) | Zhou, Jun (Zhou, Jun.) | Xiao, Chuangbai (Xiao, Chuangbai.)

收录:

EI Scopus SCIE

摘要:

Due to its ability to capture long-range dependencies, self-attention mechanism-based transformer models are introduced for hyperspectral image (HSI) classification. However, the self-attention mechanism has only spatial adaptability but ignores channel adaptability, thus cannot well extract complex spectral-spatial information in HSIs. To tackle this problem, in this article, we propose a novel spectral-spatial large kernel attention network (SSLKA) for HSI classification. SSLKA consists of two consecutive cooperative spectral-spatial attention blocks with large convolution kernels, which can efficiently extract features in spectral and spatial domains simultaneously. In each cooperative spectral-spatial attention block, we employ the spectral attention branch and the spatial attention branch to generate the attention maps, respectively, and then fuse the extracted spatial features with the spectral features. With large kernel attention (LKA), we can enhance the classification performance by fully exploiting local contextual information, capturing long-range dependencies, as well as being adaptive in the channel dimension. Experimental results on widely used benchmark datasets show that our method achieves higher classification accuracy in terms of overall accuracy (OA), average accuracy (AA), and Kappa than several state-of-the-art methods.

关键词:

Hyperspectral image (HSI) classification Convolutional neural networks Task analysis Convolution spectral-spatial attention Feature extraction Hyperspectral imaging Kernel Image classification large kernel attention (LKA)

作者机构:

  • [ 1 ] [Wu, Chunran]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Tong, Lei]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Xiao, Chuangbai]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 4 ] [Zhou, Jun]Griffith Univ, Sch Informat & Commun Technol, Nathan, Qld 4111, Australia

通讯作者信息:

  • [Tong, Lei]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China;;

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

ISSN: 0196-2892

年份: 2024

卷: 62

8 . 2 0 0

JCR@2022

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 10

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 1

归属院系:

在线人数/总访问数:424/4954138
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司