SXSFormer: Spectral Squeeze and Expansion Swin Transformer Network for Hyperspectral Image Classification
Ullah F. Ullah I. Khan K. Wang Q. Ali Algamdi S. Aldossary H. Pau G.
2025Institute of Electrical and Electronics Engineers Inc.
IEEE Transactions on Consumer Electronics
2025#71Issue 37710 - 7729 pp.
Hyperspectral images (HSIs) are highly complex, containing an enhanced spectral dimension compared to conventional images. Deep learning methods are increasingly being applied to process this three-dimensional data for hyperspectral image classification (HSIC). Existing convolutional and transformer-based methods often struggle with capturing fine-grained spectral-spatial dependencies, achieving high accuracy while balancing computational complexity. In order to solve these problems, we propose a novel SXSFormer network for HSIC. This novel approach integrates Squeeze and Expansion (SX) blocks into the Swin Transformer architecture to enhance feature extraction and attention mechanisms in the model. At its core, the novel SX Block recalibrates channel-wise features by temporarily expanding and then compressing channel dimensionality, allowing the model to focus on informative spectral bands and capture complex interdependencies. The SXSFormer, equipped with window-based multi-head self-attention, efficiently captures long-range dependencies with reduced computational complexity by partitioning input data into non-overlapping windows. Additionally, the SX block’s integration within the Swin Transformer enables improved global contextual understanding by selectively weighting the feature maps. We further refine the architecture using various components, such as patch extraction and embedding layers, and a patch merging strategy, ensuring efficient multi-scale feature extraction. Extensive experiments on four benchmark HSI datasets (SA, IP, PU, and KSC) demonstrate that the proposed model achieves remarkable test accuracies of 99.97%, 98.15%, 99.63%, and 98.14%, respectively, outperforming existing state-of-the-art methods. Our proposed approach also shows good generalization ability when applied to new datasets. Overall, our proposed approach represents a promising direction for HSIC.
attention , Hyperspectral image classification , squeeze and expansion , swin transformer , SXSFormer
Text of the article Перейти на текст статьи
Wuxi University, School of Internet of Things Engineering, Jiangsu Foreign Expert Lab, School of Internet of Things Engineering Foreign Expert Lab, Wuxi, 214105, China
Chengdu University of Technology, School of Computer Science, Chengdu, 610059, China
Nazarbayev University, School of Engineering and Digital Sciences, Department of Computer Science, Astana, 010000, Kazakhstan
Prince Sattam bin Abdulaziz University, College of Computer Science and Engineering, Department of Software Engineering, Al Kharj, 16273, Saudi Arabia
Imam Abdulrahman Bin Faisal University, College of Science and Humanities, Computer Science Department, Al Jubail, 31961, Saudi Arabia
Kore University of Enna, Department of Engineering and Architecture, Enna, 94100, Italy
Wuxi University
Chengdu University of Technology
Nazarbayev University
Prince Sattam bin Abdulaziz University
Imam Abdulrahman Bin Faisal University
Kore University of Enna
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026