Answers are grounded in this paper and cite their sources.
Among deep learning-based hyperspectral image (HSI) classification models, convolutional neural networks (CNNs), Transformers, Mamba, and large kernel CNNs (LKCNNs) models have been widely explored for HSI classification. Nonetheless, these models suffer from several challenges: for example, 1) CNNs have a weak learning ability in capturing global information between land covers, due to their limited receptive field derived from small kernel convolutions; 2) Transformers face quadratic computational complexity introduced by their self-attention mechanisms; and 3) LKCNNs require further enhancement in extracting global features, owing to the insufficient size of their receptive fields. To tackle these limitations, we propose a novel multi-scale large kernel vertical-horizontal attention network (LKVHAN) for HSI classification. The proposed LKVHAN consists of a <tex-math notation="LaTeX">1× 1</tex-math> convolution module and a multi-scale large kernel vertical-horizontal attention-based convolution (MSLKVHAC). The <tex-math notation="LaTeX">1× 1</tex-math> convolution module is designed to facilitate band reduction, noise suppression, and spectral feature learning. Furthermore, the MSLKVHAC, leveraging a large vertical kernel size of <tex-math notation="LaTeX">17× 1</tex-math> and a large horizontal kernel size of <tex-math notation="LaTeX">1× 17</tex-math>, extracts both local and global spatial features by incorporating a vertical attention-based convolution module (VACM) and a horizontal attention-based convolution module (HACM). Extensive experimental results demonstrate that the proposed LKVHAN significantly outperforms ten state-of-the-art approaches across four widely used HSI datasets.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: