Multiscale Dynamic Graph Convolutional Network for Hyperspectral Image Classification

By Sheng Wan, Chen Gong, Ping Zhong, Bo Du, Lefei Zhang, Jian Yang. IEEE Transactions on Geoscience and Remote Sensing, 2019

463 citations recorded by the source corpus.

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, and thus, 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 that 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 multiscale 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 multiscale dynamic GCN (MDGCN). The experimental results on three typical benchmark data sets firmly demonstrate the superiority of the proposed MDGCN to other state-of-the-art methods in both qualitative and quantitative aspects.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/4fa6621e122fbc02b772540b51171a832fa0d25b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qichao Liu
2. Zhihui Wei
3. Shiqi Yu
4. Sen Jia
5. Jingxiang Yang
6. Liang Xiao
7. Zhijie Lin

In Computer Vision and Pattern Recognition

1. Qichao Liu
2. Zhihui Wei
3. Shiqi Yu
4. Sen Jia
5. Meng Xu
6. Shuguo Jiang
7. Jingxiang Yang
8. Nanying Li

In Media Technology

1. Qichao Liu
2. Zhihui Wei
3. Shiqi Yu
4. Sen Jia
5. Meng Xu
6. Shuguo Jiang
7. Jingxiang Yang
8. Nanying Li

Citations in the corpus

• CNN-Enhanced Graph Convolutional Network With Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification (2020, methodology): “Analogous to [42], we take the centroid (mean) of each superpixel as a node, that is where V i denotes the feature vector of the i th node, and V is the matrix form of the nodes V .”
• A survey: Deep learning for hyperspectral image classification with few labeled samples (2021, background): “Thus, there are many researches [124, 125, 126] utilizing graph convolution networks to classify HSI.”