Rotation-Invariant Attention Network for Hyperspectral Image Classification

首页 > 成果 > 详情

认领

导出

Link by DOI

反馈

作者信息关键词期刊信息基础信息归属信息摘要

成果类型：

期刊论文

作者：

Zheng, Xiangtao;Sun, Hao;Lu, Xiaoqiang;Xie, Wei

通讯作者：

Lu, X.

作者机构：

[Lu, Xiaoqiang; Zheng, Xiangtao] Xi'An Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Key Laboratory of Spectral Imaging Technology CAS, Xi'an, 710119, China

University of Chinese Academy of Sciences, Beijing, 100049, China

[Xie, Wei] 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

[Sun, Hao] Xi'An Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Key Laboratory of Spectral Imaging Technology CAS, Xi'an, 710119, China, University of Chinese Academy of Sciences, Beijing, 100049, China

通讯机构：

[Lu, X.] X

Xi'An Institute of Optics and Precision Mechanics, China

语种：

英文

关键词：

attention mechanism;convolutional neural network;Hyperspectral image classification;rotation-invariant network;spectral-spatial feature extraction

期刊：

IEEE Transactions on Image Processing

ISSN：

1057-7149

年：

2022

卷：

页码：

4251-4265

DOI：

10.1109/TIP.2022.3177322

基金类别：

10.13039/501100014219-National Science Fund for Distinguished Young Scholars (Grant Number: 61925112) Innovation Capability Support Program of Shaanxi (Grant Number: 2020KJXX-091) Chinese Association for Artificial Intelligence (CAAI)-Huawei Mind-Spore Open Fund

机构署名：

本校为其他机构

院系归属：

计算机学院

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 $3 \times 3$ convolution is utilized as a key component to capture spatial features for HSI classification. However, the $3 \times 3$ 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 ...

反馈

产权有误：本人成果被他人认领

数据有误：数据基本信息有误

归属有误：成果的院系归属、机构署名归属有误

其他原因：

验证码：

看不清楚，换一个

确定

取消

成果认领

标题：

用户	作者	通讯作者	--
	请选择	请选择	--

确定

取消

Rotation-Invariant Attention Network for Hyperspectral Image Classification

反馈

成果认领

提示

该栏目需要登录且有访问权限才可以访问