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

2025-02-10

AI Summary

To address challenges in hyperspectral image (HSI) classification—including difficulty in modeling high-dimensional spectral-spatial features, weak global contextual awareness, and excessive computational overhead—this paper proposes a lightweight hybrid architecture integrating state space models (SSMs) with gated recurrent units (GRUs). We innovatively introduce a graph-structured token prioritization mechanism and a cross-attention module, coupled with a spectral-spatial joint tokenization strategy, to jointly capture linear and nonlinear dynamics while maintaining high inference efficiency. Evaluated on multiple benchmark HSI datasets, the method achieves significant improvements over existing state-of-the-art approaches: classification accuracy is notably enhanced, model parameters are reduced by over 30%, and inference speed is accelerated by 2.1×. The framework demonstrates particular efficacy in label-scarce scenarios, offering a favorable trade-off between representational power and computational efficiency.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Hyperspectral image classification challenges
• High-dimensional data complexity
• Spectral-spatial feature modeling

Innovation

• Hybrid state-space and GRU modeling
• Graph-based token prioritization
• Cross-attention mechanisms for HSI