CWSSNet: Hyperspectral Image Classification Enhanced by Wavelet Domain Convolution
Yulin Tong, Fengzong Zhang, Haiqin Cheng
TL;DR
CWSSNet tackles the challenge of hyperspectral image classification by integrating a CNN-based encoder with Wavelet Threshold Binary Convolution and a Multi-Channel Attention mechanism to capture multi-scale spectral-spatial information. The approach employs wavelet-domain processing to expand receptive fields while maintaining efficiency, and a dual-branch fusion strategy to reconcile global semantics with local details. Empirical results on ZY1F data from Yugan County show state-of-the-art performance with a mean IoU of $74.50\%$, mean Accuracy of $82.73\%$, and mean F1-score of $84.94\%$, along with strong IoUs for water bodies, vegetation, and bare soil. The work demonstrates that combining wavelet-based frequency decomposition, attention-guided feature refinement, and cross-scale fusion can significantly improve hyperspectral land-cover classification, especially under limited training samples.
Abstract
Hyperspectral remote sensing technology has significant application value in fields such as forestry ecology and precision agriculture, while also putting forward higher requirements for fine ground object classification. However, although hyperspectral images are rich in spectral information and can improve recognition accuracy, they tend to cause prominent feature redundancy due to their numerous bands, high dimensionality, and spectral mixing characteristics. To address this, this study used hyperspectral images from the ZY1F satellite as a data source and selected Yugan County, Shangrao City, Jiangxi Province as the research area to perform ground object classification research. A classification framework named CWSSNet was proposed, which integrates 3D spectral-spatial features and wavelet convolution. This framework integrates multimodal information us-ing a multiscale convolutional attention module and breaks through the classification performance bottleneck of traditional methods by introducing multi-band decomposition and convolution operations in the wavelet domain. The experiments showed that CWSSNet achieved 74.50\%, 82.73\%, and 84.94\% in mean Intersection over Union (mIoU), mean Accuracy (mAcc), and mean F1-score (mF1) respectively in Yugan County. It also obtained the highest Intersection over Union (IoU) in the classifica-tion of water bodies, vegetation, and bare land, demonstrating good robustness. Additionally, when the training set proportion was 70\%, the increase in training time was limited, and the classification effect was close to the optimal level, indicating that the model maintains reliable performance under small-sample training conditions.