Saved in:
Bibliographic Details
Main Authors: Wen, Jiawen, Qiu, Suixuan, Luo, Zihang, Yang, Xiaofei, Shi, Haotian
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.24045
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910070959243264
author Wen, Jiawen
Qiu, Suixuan
Luo, Zihang
Yang, Xiaofei
Shi, Haotian
author_facet Wen, Jiawen
Qiu, Suixuan
Luo, Zihang
Yang, Xiaofei
Shi, Haotian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24045
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LGEST: Dynamic Spatial-Spectral Expert Routing for Hyperspectral Image Classification
Wen, Jiawen
Qiu, Suixuan
Luo, Zihang
Yang, Xiaofei
Shi, Haotian
Computer Vision and Pattern Recognition
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.
title LGEST: Dynamic Spatial-Spectral Expert Routing for Hyperspectral Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.24045