GCN:基于非局部图卷积神经网络的高光谱图像分类 | TGRS 2020
Posted 科研之高光谱
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了GCN:基于非局部图卷积神经网络的高光谱图像分类 | TGRS 2020相关的知识,希望对你有一定的参考价值。
△ 点 上方蓝字 关注科研之高光谱
分享前沿论文 享受科研之美
你好,欢迎来到高光谱图像处理论文推荐。今天介绍的论文来自西安光机所李学龙老师团队,提出了一种基于非局部图卷积神经网络高光谱图像分类方法。
这篇论文发表在IEEE TGRS期刊上,投稿于2019年7月16日,收录于2019年12月9日。
Over the past few years making use of deep networks, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), classifying hyperspectral images has progressed significantly and gained increasing attention. In spite of being successful, these networks need an adequate supply of labeled training instances for supervised learning, which, however, is quite costly to collect. On the other hand, unlabeled datacan be accessed in almost arbitrary amounts. Hence it would be conceptually ofgreat interest to explore networks that are able to exploit labeled and unlabeled data simultaneously for hyperspectral image classification.
In this article, we propose a novelgraph-based semisupervised network called nonlocal graph convolutional network (nonlocal GCN). Unlike existing CNNs and RNNs that receive pixels or patches ofa hyperspectral image as inputs, this network takes the whole image (including both labeled and unlabeled data) in. More specifically, a nonlocal graph is first calculated. Given this graph representation, a couple of graph convolutional layers are used to extract features. Finally, the semisupervised learning of the network is done by using a cross-entropy error over all labeled instances. Note that the nonlocal GCN is end-to-end trainable.
We demonstrate in extensive experiments that compared with state-of-the-art spectral classifiers and spectral–spatial classification networks, the nonlocal GCN is able to offer competitive resultsand high-quality classification maps (with fine boundaries and without noisy scattered points of misclassification).
划重点
通过一个基于图的半监督网络进行高光谱图像分类。与现有的网络(如CNNs和RNNs)不同,CNNs和RNNs接收图像的局部部分(例如像素和块)作为输入,本文网络接收整个高光谱图像。
与感受野是图像局部区域的CNN不同,本文方法使用非局部的、数据驱动的图表示来完成高光谱图像分类任务。
在三个基准数据集上进行了实验,结果显示了GCN网络的高性能。此外,我们的网络可以提供更高质量的分类图。
后台回复“高光谱图像论文”,获取pdf格式论文。
祝好!
往 期 解 读
1.
2.
3.
4.
5.
以上是关于GCN:基于非局部图卷积神经网络的高光谱图像分类 | TGRS 2020的主要内容,如果未能解决你的问题,请参考以下文章
GCN图卷积网络初探——基于图(Graph)的傅里叶变换和卷积