Hybrid State-Space and GRU-based Graph Tokenization Mamba for Hyperspectral Image Classification
This work provides a significant solution for hyperspectral image classification, which is crucial for applications such as environmental monitoring, agriculture, and urban planning.
The authors tackled the challenge of hyperspectral image classification by proposing a hybrid model called GraphMamba, which achieved state-of-the-art results. GraphMamba outperformed existing models, offering a scalable and robust solution for complex hyperspectral image classification tasks.
Hyperspectral image (HSI) classification plays a pivotal role in domains such as environmental monitoring, agriculture, and urban planning. However, it faces significant challenges due to the high-dimensional nature of the data and the complex spectral-spatial relationships inherent in HSI. Traditional methods, including conventional machine learning and convolutional neural networks (CNNs), often struggle to effectively capture these intricate spectral-spatial features and global contextual information. Transformer-based models, while powerful in capturing long-range dependencies, often demand substantial computational resources, posing challenges in scenarios where labeled datasets are limited, as is commonly seen in HSI applications. To overcome these challenges, this work proposes GraphMamba, a hybrid model that combines spectral-spatial token generation, graph-based token prioritization, and cross-attention mechanisms. The model introduces a novel hybridization of state-space modeling and Gated Recurrent Units (GRU), capturing both linear and nonlinear spatial-spectral dynamics. GraphMamba enhances the ability to model complex spatial-spectral relationships while maintaining scalability and computational efficiency across diverse HSI datasets. Through comprehensive experiments, we demonstrate that GraphMamba outperforms existing state-of-the-art models, offering a scalable and robust solution for complex HSI classification tasks.