Multiscale Dynamic Graph Convolutional Network for Hyperspectral Image Classification

Abstract

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.

Hyperspectral Image Classification With Spectral and Spatial Graph Using Inductive Representation Learning Network

“…According to Ref. [38], the GCN method needs large memory, it may not be suitable for the large dataset such as Pavia University. Therefore, we only display other HSI methods.…”

“…Therefore, GCN can be applied to the non-Euclidean data using the predefined graph. Wan et al [38] proposed a hyperspectral image classification using multi-scale dynamic GCN. It uses multiple input graphs with different neighborhood scales to enhance the performance.…”

A Hyperspectral Image Classification Approach Based on Feature Fusion and Multi-Layered Gradient Boosting Decision Trees

“…The proposed model was compared with SVM-RBF [ 30 ], SVM-EMP [ 31 ], CNN [ 32 ], 3D-CNN [ 33 ], FuNet-C [ 34 ], and MDGCN [ 35 ] to explore whether the proposed model was effective. SVM-RBF used the spectral features of the hyperspectral data as input for training.…”

DFL-LC: Deep Feature Learning With Label Consistencies for Hyperspectral Image Classification

“…Thus, this method takes full advantage of the current pixel spatial information in the process of approximate convolution. Wan et al proposed a multi-scale dynamic graph convolutional network (MDGCN) whose graph is dynamically updated during graph convolution, and its input graphs have different neighbourhood scales to utilize multi-scale information in HSI [38]. GCN can capture relationships based on the predefined graph that contains global information, but the pixels relationships for graph construction cannot be well ensured.…”