HyperTransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Hyperspectral Image Classification

HyperTransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Hyperspectral Image Classification

Recent advances in hyperspectral image (HSI) classification have demonstrated the effectiveness of hybrid architectures that integrate convolutional neural networks (CNNs) and Transformers, leveraging CNNs for local feature extraction and Transformers for global dependency modeling. However, existin...

Full description

Saved in:
Bibliographic Details
Main Authors: Xin Dai, Zexi Li, Lin Li, Shuihua Xue, Xiaohui Huang, Xiaofei Yang
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Remote Sensing
Subjects:
convolution neural network (CNN)
hyperspectral image classificationg
transformer network
mamba network
Online Access:https://www.mdpi.com/2072-4292/17/14/2361
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent advances in hyperspectral image (HSI) classification have demonstrated the effectiveness of hybrid architectures that integrate convolutional neural networks (CNNs) and Transformers, leveraging CNNs for local feature extraction and Transformers for global dependency modeling. However, existing fusion approaches face three critical challenges: (1) insufficient synergy between spectral and spatial feature learning due to rigid coupling mechanisms; (2) high computational complexity resulting from redundant attention calculations; and (3) limited adaptability to spectral redundancy and noise in small-sample scenarios. To address these limitations, we propose HyperTransXNet, a novel CNN-Transformer hybrid architecture that incorporates adaptive spectral-spatial fusion. Specifically, the proposed HyperTransXNet comprises three key modules: (1) a Hybrid Spatial-Spectral Module (HSSM) that captures the refined local spectral-spatial features and models global spectral correlations by combining depth-wise dynamic convolution with frequency-domain attention; (2) a Mixture-of-Experts Routing (MoE-R) module that adaptively fuses multi-scale features by dynamically selecting optimal experts via Top-K sparse weights; and (3) a Spatial-Spectral Tokens Enhancer (SSTE) module that ensures causality-preserving interactions between spectral bands and spatial contexts. Extensive experiments on the Indian Pines, Houston 2013, and WHU-Hi-LongKou datasets demonstrate the superiority of HyperTransXNet.
ISSN:2072-4292

Similar Items