GTransCD: Graph Transformer-Guided Multitemporal Information United Framework for Hyperspectral Image Change Detection

• Published in: IEEE transactions on geoscience and remote sensing Vol. 62; pp. 1 - 13
• Main Authors: Zhao, Xiaoyang, Li, Siyao, Geng, Tingting, Wang, Xianghai
• Format: Journal Article
• Language: English
• Published: New York The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
• Subjects: Artificial neural networks; Change detection; Data integration; Detection; Feature extraction; Graph neural networks; Hyperspectral imaging; Image processing; Information processing; Land cover; Machine learning; Modules; Neural networks; Receptive field; Remote sensing; Semi-supervised learning; Source code; Transformers
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2023.3339247

Using multitemporal hyperspectral images (HSIs) to obtain fine-grained land cover change information is an essential task in remote sensing (RS) image processing. Convolutional neural networks (CNNs), which have strong feature extraction and nonlinear regression capabilities, have recently aided in the advancement of this subject. However, the performance of these supervised methods is usually limited by small receptive field and less labeled samples. To this end, how to break through the aforementioned bottleneck and build a more suitable change detection (CD) framework for HSI is a crucial and challenging issue. To this end, a graph transformer-guided multitemporal information united framework for HSI-CD (GTransCD) is proposed, which mainly consists of the following three components: 1) applying transformer to the graph structure, a salient relationship strengthening graph transformer (GTrans) module is created, making it possible for the network to capture distant change information, and on this basis, local- and global-range information are aggregated simultaneously; 2) a gated change information fusion (GCF) unit is designed to inject the GTrans-guided change features into the original bitemporal concatenated features to further enhance the representation of change information in the network; and 3) a general HSI-CD framework that can organically blend change features guided by GTrans module with original features is proposed, with the intention of reducing the reliance on training samples by utilizing the semi-supervised learning mode of graph neural networks. numerous experiments demonstrate the proposed GTransCD surpasses the state-of-the-art methods and has a high level even at low sampling rates. The source code of the proposed framework will be released at https://github.com/zxylnnu/GTransCD .