Spectral–Spatial Synergy Guided Attention Network for Hyperspectral Image Classification
Zhenqiu Shu, Kexin Zeng, Jun Zhou, Yuyang Wang, Ming-Yi Tai, Zhengtao Yu
Abstract
The attention mechanism has gained significant popularity in hyperspectral image classification (HSIC) for its ability to adaptively highlight key features. However, it often incurs expensive computational costs due to the iterative operations. Moreover, the high inter-class similarity and indistinct class boundaries in hyperspectral images (HSIs) pose challenges for classification tasks. To tackle these issues, we propose a spectral-spatial synergy guided attention network (SSSGAN) for HSIC. It initially employs a spectral-spatial synergistic mechanism to jointly extract local spectral and spatial features of HSIs, and then applies a guided attention mechanism to effectively reduce computational complexity and further improve its discriminative capabilities. Specifically, a stacked residual spectral feature extractor stacks scale-variable convolution blocks within the channel-connected residual structure. It precisely localizes boundaries and reduces boundary blur by extracting and fusing local multi-level spectral features. A hierarchical dual feature enhancement module employs parallel multi-scale branches combined with dual shift operations to extract multi-scale spatially enhanced features, thereby enriching the diversity of feature representations and improving the discriminability of inter-class features. Finally, a feature-aware guided attention module reduces the computational cost of the attention mechanism by incorporating the guiding token and convolutional operations. By introducing local regularization into the attention map, the convolution enhances the robustness and effectiveness of global and contextual information extraction from HSIs. Experiments conducted on four publicly available benchmark datasets (PU, HU2013, SV, and LK) demonstrate that the proposed SSSGAN method achieves overall accuracies of 98.96%, 95.93%, 98.72%, and 98.31%, respectively, thereby validating its effectiveness in HISC tasks. The source code for this work can be found at https://github.com/szq0816/DSGAN.