LGEST: Dynamic Spatial-Spectral Expert Routing for Hyperspectral Image Classification

2026-03-25

AI Summary

Existing hyperspectral image classification methods face limitations in fusing local–global representations, modeling the scale discrepancies between spectral and spatial domains, and mitigating the Hughes phenomenon under high-dimensional heterogeneity. To address these challenges, this work proposes the LGEST framework, which employs a deep spectral-spatial autoencoder to generate compact embeddings, designs a cross-interacting mixture-of-experts feature pyramid for dynamic multi-scale information fusion, and introduces a local–global collaborative expert system with learnable gating to enable sparsity-aware routing based on feature saliency. By adaptively weighting spectral discriminability and spatial saliency, the proposed method achieves significant performance gains over state-of-the-art approaches across four benchmark datasets, demonstrating its effectiveness and superiority.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Representation Learning for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Deep learning methods, including Convolutional Neural Networks, Transformers and Mamba, have achieved remarkable success in hyperspectral image (HSI) classification. Nevertheless, existing methods exhibit inflexible integration of local-global representations, inadequate handling of spectral-spatial scale disparities across heterogeneous bands, and susceptibility to the Hughes phenomenon under high-dimensional sample heterogeneity. To address these challenges, we propose Local-Global Expert Spatial-Spectral Transformer (LGEST), a novel framework that synergistically combines three key innovations. The LGEST first employs a Deep Spatial-Spectral Autoencoder (DSAE) to generate compact yet discriminative embeddings through hierarchical nonlinear compression, preserving 3D neighborhood coherence while mitigating information loss in high-dimensional spaces. Secondly, a Cross-Interactive Mixed Expert Feature Pyramid (CIEM-FPN) leverages cross-attention mechanisms and residual mixture-of-experts layers to dynamically fuse multi-scale features, adaptively weighting spectral discriminability and spatial saliency through learnable gating functions. Finally, a Local-Global Expert System (LGES) processes decomposed features via sparsely activated expert pairs: convolutional sub-experts capture fine-grained textures, while transformer sub-experts model long-range contextual dependencies, with a routing controller dynamically selecting experts based on real-time feature saliency. Extensive experiments on four benchmark datasets demonstrate that LGEST consistently outperforms state-of-the-art methods.

Problem

• hyperspectral image classification
• local-global representation
• spectral-spatial scale disparity
• Hughes phenomenon
• high-dimensional heterogeneity

Innovation

• Expert Routing
• Spatial-Spectral Fusion
• Mixture of Experts
• Hyperspectral Image Classification
• Local-Global Representation