| 基于各类特征对齐迁移网络的多时相遥感图像分类 |
| |
| 引用本文： | 郭艳,宋佳珍,马丽,杨敏.基于各类特征对齐迁移网络的多时相遥感图像分类[J].地球科学,2021,46(10):3730-3739. |
| |
| 作者姓名： | 郭艳 宋佳珍 马丽 杨敏 |
| |
| 作者单位： | 1.中国地质大学计算机学院, 湖北武汉 430078 |
| |
| 基金项目： | 国家自然科学基金项目61771437 |
| |
| 摘 要： | 为了在目标域遥感图像不存在标记数据的情况下实现自动分类，论文提出一种基于特征对齐的迁移网络.网络以各类类心对齐和协方差对齐作为迁移策略，全面描述域间各类别之间的对应关系，实现知识迁移.另外，网络采用线性修正单元作为激活函数，能够产生稀疏特征，提高分类效果.该迁移网络能够同时获得对齐的特征和自适应分类器，不需要目标域的标记数据，实现无监督迁移学习.在多时相的Hyperion高光谱遥感图像和WorldView-2多光谱遥感图像上的实验结果证明了该迁移网络的有效性.
|
| 关 键 词： | 迁移网络 分类 各类特征对齐 遥感 |
| 收稿时间： | 2020-11-13 |
Class-Wise Feature Alignment Based Transfer Network for Multi-Temporal Remote Sensing Image Classification |
| |
| Guo Yan,Song Jiazhen,Ma Li,Yang Min.Class-Wise Feature Alignment Based Transfer Network for Multi-Temporal Remote Sensing Image Classification[J].Earth Science-Journal of China University of Geosciences,2021,46(10):3730-3739. |
| |
| Authors: | Guo Yan Song Jiazhen Ma Li Yang Min |
| |
| Abstract: | A transfer neural network based on feature alignment is proposed for classification of multi-temporal remote sensing image. In the network, the mean vector and covariance matrix of the sample data of each class are used to describe the data distribution, and the domain shift in terms of the first and second statistics can be reduced. In addition, rectified linear unit is utilized as the activation function, which can produce sparse features and improve the classification performance. In the transfer neural network, both aligned features and adaptive classifiers can be obtained simultaneously and unsupervised domain adaptation is achieved when there is no labeled data in the target image. The experimental results of multi-temporal Hyperion hyperspectral remote sensing images and WorldView-2 multispectral remote sensing images demonstrate the effectiveness of the proposed transfer neural network. |
| |
| Keywords: | |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《地球科学》浏览原始摘要信息 |
| 点击此处可从《地球科学》下载免费的PDF全文 |
|
