2026· IEEE Transactions on Geoscience and Remote Sensing· Vol 64, pp. 5525318-5525318· 0 citations· 57 references
Abstract
Hyperspectral image classification (HSIC) faces critical challenges, including restricted receptive fields in patch-level methods and coarse feature representations alongside subpixel blindness in conventional image-level networks. To address these bottlenecks, we propose I2SNet, a novel lightweight image-level end-to-end architecture driven by a coarse-to-fine hierarchical feature learning paradigm. The network systematically extracts spatial–spectral representations across patch, pixel, and subpixel scales. Specifically, a spatial–spectral linear transformer (SSLT) and a spatial–spectral deformable Mamba (SSDM) are unified to efficiently capture global patch interactions with linear complexity. Subsequently, multiscale spatial–spectral dynamic convolutions (MS3DCs) extract fine-grained local contexts. Furthermore, a subpixel nonlinear mixing model (SNLMM) is introduced to explicitly address subpixel blindness by modeling the physical mixing mechanisms of diverse materials. Extensive experiments on four benchmark datasets demonstrate that I2SNet achieves strong classification accuracy while maintaining an efficient and compact computational profile compared to state-of-the-art approaches. To facilitate reproducibility, our code is publicly available at https://github.com/flyzzie/I2SNet
Hyperspectral image classification (HSIC) is a core task in remote sensing. Traditional convolutional neural networks (CNNs) are constrained by limited local receptive fields and struggle to capture long-range dependencies within hyperspectral images (HSIs). Although Mamba-based HSIC models can effectively model long-r...
Lian-Hui Liang, Chen-Yang Meng, Shuai Yuan et al.· IEEE Transactions on Geoscie...· 0 citations
A novel hyperspectral classification model, termed C3Former, is proposed to explicitly model spectral–spatial dependencies and enable multiscale feature fusion through adaptive receptive field modulation, and a cross-layer convolutional-transformer encoder module is developed to reinforce spectral–spatial dependencies...
Chen-Chen Fu, Qing-Qing Hong, Shivakumara Palaiahnakote et al.· IEEE Journal of Selected Top...· 0 citations
The results suggest that decoupled spatial–spectral representation and adaptive multi-scale fusion can improve hyperspectral image classification under the evaluated benchmark settings.
Hyperspectral image (HSI) classification has been widely applied in numerous fields. Although deep learning-based methods have improved classification performance, existing approaches still struggle to balance accuracy and computational efficiency. Convolutional neural network (CNN)-based methods are limited by local r...
Han-Zhong Li, Hua Huang, Hong-Feng Li et al.· IEEE Transactions on Geoscie...· 0 citations
A state space modeling framework is introduced into bitemporal hyperspectral analysis to efficiently model long-range spectral–spatial dependencies and discriminative temporal interactions with linear computational complexity in HSI-CD.
Xiao-Dong Wei, Rui-Zhe Liu, Ji-Yuan Li et al.· IEEE Journal of Selected Top...· 0 citations
Hyperspectral image (HSI) classification remains challenging because accurate recognition requires both global contextual modeling and computationally efficient processing of high-dimensional spectral–spatial data. Transformer-based methods can capture long-range interactions, but their quadratic token-mixing cost limi...
Lu Zhou, Ji-Yan Li, Xiao-Fei Yang et al.· IEEE Geoscience and Remote S...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.