arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1905.06133eess.IVcs.LGstat.ML
收藏

基于多尺度动态图卷积网络的高光谱图像分类

Multi-scale Dynamic Graph Convolutional Network for Hyperspectral Image Classification

Nanjing University of Science and Technology(南京理工大学);National University of Defense Technology(中国人民解放军国防科技大学);Wuhan University(武汉大学)

Sheng Wan, Chen Gong, Ping Zhong, Bo Du, Lefei Zhang, Jian Yang

摘要:

卷积神经网络(CNN)已经证明了令人印象深刻的能力,表示高光谱图像,并取得了可喜的结果,在高光谱图像分类。然而,传统的CNN模型只能对具有固定大小和权重的规则正方形图像区域进行卷积运算,因此不能普遍适应具有各种对象分布和几何外观的不同局部区域。因此,它们的分类性能仍有待提高,特别是在类边界。为了克服这一缺点,我们考虑采用最近提出的图卷积网络(GCN)的高光谱图像分类,因为它可以进行任意结构的非欧数据的卷积,并适用于不规则的图像区域表示的图形拓扑信息。与常用的GCN模型工作在固定图上不同,我们使图能够随着图卷积过程而动态更新,因此这两个步骤可以相互受益,逐渐产生有区别的嵌入特征以及细化的图。此外,为了全面部署高光谱图像继承的多尺度信息,我们建立了具有不同邻域尺度的多个输入图,以广泛利用多个尺度下的多样化光谱-空间相关性。因此,我们的方法被称为“多尺度动态图卷积网络”(MDGCN)。在三个典型的基准数据集上的实验结果证明了MDGCN在定性和定量方面都优于其他最先进的方法。

英文摘要:

Convolutional Neural Network (CNN) has demonstrated impressive ability to represent hyperspectral images and to achieve promising results in hyperspectral image classification. However, traditional CNN models can only operate convolution on regular square image regions with fixed size and weights, so they cannot universally adapt to the distinct local regions with various object distributions and geometric appearances. Therefore, their classification performances are still to be improved, especially in class boundaries. To alleviate this shortcoming, we consider employing the recently proposed Graph Convolutional Network (GCN) for hyperspectral image classification, as it can conduct the convolution on arbitrarily structured non-Euclidean data and is applicable to the irregular image regions represented by graph topological information. Different from the commonly used GCN models which work on a fixed graph, we enable the graph to be dynamically updated along with the graph convolution process, so that these two steps can be benefited from each other to gradually produce the discriminative embedded features as well as a refined graph. Moreover, to comprehensively deploy the multi-scale information inherited by hyperspectral images, we establish multiple input graphs with different neighborhood scales to extensively exploit the diversified spectral-spatial correlations at multiple scales. Therefore, our method is termed 'Multi-scale Dynamic Graph Convolutional Network' (MDGCN). The experimental results on three typical benchmark datasets firmly demonstrate the superiority of the proposed MDGCN to other state-of-the-art methods in both qualitative and quantitative aspects.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑