Hybrid State-Space and GRU-based Graph Tokenization Mamba for Hyperspectral Image Classification

TL;DR

This paper introduces GraphMamba, a hybrid spectral-spatial tokenization model combining state-space and GRU mechanisms, which effectively captures complex relationships in hyperspectral images while being scalable and computationally efficient.

Contribution

The work presents a novel hybrid model that integrates state-space and GRU for improved spectral-spatial feature extraction in hyperspectral image classification.

Findings

GraphMamba outperforms existing models on multiple HSI datasets.

The hybrid approach effectively captures complex spectral-spatial relationships.

The model maintains scalability and efficiency in high-dimensional data.

Abstract

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.