Spectral-Guided Multiscale Feature-Aware Transformer for Hyperspectral Image Classification

作者：Zhenqiu Shu, Kexin Zeng, Yuyang Wang, Songze Tang, Zhengtao Yu, Liang Xiao · 发表于：IEEE Transactions on Neural Networks and Learning Systems · 年份：2025 · DOI：10.1109/tnnls.2025.3630239 · 被引用次数：2 · 研究领域：Remote-Sensing Image Classification、Face and Expression Recognition、Advanced Image Fusion Techniques

Transformer-based methods have recently shown remarkable success in hyperspectral image classification (HSIC). However, their applications, in practice, still face two significant challenges. First, although the multihead mechanism in self-attention improves model robustness during training, it may overlook the continuity of spectral bands. Second, existing methods often struggle to effectively balance global and local information during multiscale feature extraction, limiting further improvements in classification performance. To address these issues, we propose a novel spectral-guided multiscale feature-aware Transformer (SMFAT) framework for HSIC. Specifically, a global low-rank spectral learning (GLSL) module is introduced to project hyperspectral image patches into a low-rank subspace, reducing spectral redundancy and capturing global spectral correlations. Furthermore, we introduce the multiscale feature-aware self-attention (MFASA) mechanism, which dynamically integrates fine- and coarse-grained features to enhance multiscale feature modeling. Finally, a spectral-guided fusion (SGF) module leverages the global spectral information extracted by the GLSL module to guide MFASA in more effectively capturing interspectral correlations and spectral continuity. This approach facilitates a more effective integration of spectral and spatial features in HSIs. Experiments on three well-known HSI datasets verify that the proposed SMFAT method significantly outperforms several stat...