Hybrid CNN-GCN Network for Hyperspectral Image Classification
In recent years, convolutional neural networks (CNNs) have been impressive due to their excellent feature representation abilities, but it is difficult to learn long-distance spatial structures information. Unlike CNN, graph convolutional networks (GCNs) can well handle the intrinsic manifold struct...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10915579/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In recent years, convolutional neural networks (CNNs) have been impressive due to their excellent feature representation abilities, but it is difficult to learn long-distance spatial structures information. Unlike CNN, graph convolutional networks (GCNs) can well handle the intrinsic manifold structures of hyperspectral images (HSIs). However, the existing GCN-based classification methods do not fully utilize the edge relationship, which makes their performance is limited. In addition, a small number of training samples is also a reason for hindering high-performance HSI classification. Therefore, this article proposes a hybrid CNN-GCN network (HCGN) for HSI classification. First, a graph edge enhanced module (GEEM) is designed to enhance the superpixel-level features of graph edge nodes and improve the spatial discrimination ability of ground objects. In particular, considering multiscale information is complementary, a multiscale GEEM based on GEEM is proposed to fully utilize texture structures of different sizes. Then, in order to enhance the pixel-level multi hierarchical fine feature representation of images, a multiscale cross fusion module based on the CNN framework is proposed. Finally, the extracted pixel-level features and superpixel-level features are cascaded. Through a series of experiments, it has been proved that compared with some state-of-the-art methods, HCGN combines the advantages of CNN and GCN frameworks, can provide superior classification performance under limited training samples, and demonstrates the advantages and great potential of HCGN. |
|---|---|
| ISSN: | 1939-1404 2151-1535 |