Pairwise Comparison Network for Remote Sensing Scene Classification

OPT OpenIR > 光谱成像技术研究室

	Pairwise Comparison Network for Remote Sensing Scene Classification
	Zhang, Yue 1,2; Zheng, Xiangtao1 ; Lu, Xiaoqiang1
作者部门	光谱成像技术研究室
	2022-05-17
出处	arXiv
ISSN	23318422
产权排序	1
摘要	Remote sensing scene classification aims to assign a specific semantic label to a remote sensing image. Recently, convolutional neural networks have greatly improved the performance of remote sensing scene classification. However, some confused images may be easily recognized as the incorrect category, which generally degrade the performance. The differences between image pairs can be used to distinguish image categories. This paper proposed a pairwise comparison network, which contains two main steps: pairwise selection and pairwise representation. The proposed network first selects similar image pairs, and then represents the image pairs with pairwise representations. The self-representation is introduced to highlight the informative parts of each image itself, while the mutual-representation is proposed to capture the subtle differences between image pairs. Comprehensive experimental results on two challenging datasets (AID, NWPU-RESISC45) demonstrate the effectiveness of the proposed network. The code are provided in https://github.com/spectralpublic/PCNet.git. Copyright © 2022, The Authors. All rights reserved.
收录类别	EI
语种	英语
出版者	arXiv
EI入藏号	2147483647
文献类型	预印本
条目标识符	http://ir.opt.ac.cn/handle/181661/95983
专题	光谱成像技术研究室
作者单位	1.The Key Laboratory of Spectral Imaging Technology CAS, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Shaanxi, Xi’an; 710119, China; 2.The University of Chinese Academy of Sciences, Beijing; 100049, China
推荐引用方式 GB/T 7714	Zhang, Yue,Zheng, Xiangtao,Lu, Xiaoqiang. Pairwise Comparison Network for Remote Sensing Scene Classification. 2022.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
2205.08147v1.pdf（458KB）	预印本		限制开放	CC BY-NC-SA	请求全文