Multiscale Random-Shape Convolution and Adaptive Graph Convolution Fusion Network for Hyperspectral Image Classification | |
Gao, Hongmin1; Sheng, Runhua1; Chen, Zhonghao1; Liu, Haiyun1; Xu, Shufang1,2; Zhang, Bing3 | |
作者部门 | 光谱成像技术研究室 |
2024 | |
发表期刊 | IEEE Transactions on Geoscience and Remote Sensing
![]() |
ISSN | 01962892;15580644 |
卷号 | 62 |
产权排序 | 2 |
摘要 | Convolution neural networks (CNNs) are extensively utilized in hyperspectral image (HSI) classification due to their remarkable capability to extract features from patterns with fixed shapes. These networks have been shown to effectively capture features at the pixel level. However, the fixed shape of convolution kernels poses a challenge for CNNs to adapt to the diverse shapes found in HSIs. Graph neural networks (GNNs), particularly graph convolution networks (GCNs), possess robust feature extraction capabilities on graph structures and are extensively applied in HSI classification. However, one significant challenge in using GNNs is the selection of appropriate neighboring nodes for information aggregation. To address the existing challenges of GCN and CNN and leverage their respective advantages, this article introduces a novel patch-based CNN-GCN fusion classification network, named multiscale random-shape convolution and adaptive graph convolution fusion network (MRCAGCFN). It consists of a spectral transformation module (STM) and three main modules we proposed: a multiscale random-shape convolution (RSC) module for extracting convolution features, where the shape of the convolution kernel is randomized and a multiscale approach is applied to enhance adaptability to data with diverse shapes; an adaptive feature-fusion graph convolution module (AFGCM) for extracting graph convolution features, where the weights for neighborhood aggregation are learned adaptively to reduce feature fusion from dissimilar nodes and strengthen feature fusion from similar nodes; and an adaptive local feature processing module for processing features, where two different methods are employed to convert patch-level features to pixel-level features, thereby improving feature representation. MRCAGCFN combines the strengths of CNN and GCN while introducing enhancements to better accommodate diverse feature shapes. Experimental results on three HSI classification datasets demonstrate that our proposed MRCAGCFN outperforms some existing methods. The codes of our MRCAGCFN will be available at https://github.com/shengrunhua/MRCAGCFN. © 1980-2012 IEEE. |
关键词 | Convolution neural network (CNN) feature fusion graph convolution network (GCN) hyperspectral image(HSI) classification |
DOI | 10.1109/TGRS.2024.3390928 |
收录类别 | EI |
语种 | 英语 |
出版者 | Institute of Electrical and Electronics Engineers Inc. |
EI入藏号 | 20241715959755 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/97432 |
专题 | 光谱成像技术研究室 |
通讯作者 | Xu, Shufang |
作者单位 | 1.Hohai University, Information Department, Nanjing; 211100, China; 2.Shaanxi Key Laboratory of Optical Remote Sensing and Intelligent Information Processing, Xi'an; 710119, China; 3.Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing; 100094, China |
推荐引用方式 GB/T 7714 | Gao, Hongmin,Sheng, Runhua,Chen, Zhonghao,et al. Multiscale Random-Shape Convolution and Adaptive Graph Convolution Fusion Network for Hyperspectral Image Classification[J]. IEEE Transactions on Geoscience and Remote Sensing,2024,62. |
APA | Gao, Hongmin,Sheng, Runhua,Chen, Zhonghao,Liu, Haiyun,Xu, Shufang,&Zhang, Bing.(2024).Multiscale Random-Shape Convolution and Adaptive Graph Convolution Fusion Network for Hyperspectral Image Classification.IEEE Transactions on Geoscience and Remote Sensing,62. |
MLA | Gao, Hongmin,et al."Multiscale Random-Shape Convolution and Adaptive Graph Convolution Fusion Network for Hyperspectral Image Classification".IEEE Transactions on Geoscience and Remote Sensing 62(2024). |
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 | ||
Multiscale Random-Sh(8641KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
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。
修改评论