MSLKCNN: a simple and powerful multi-scale large kernel CNN for hyperspectral image classification.

Liu, Xun; Ng, Alex Hay-Man; Lei, Fangyuan; Ren, Jinchang; Guo, Li; Du, Zheyuan

Abstract

Deep learning-based hyperspectral image (HSI) classification models typically utilize multiple feature extraction layers to learn the features of land covers. Nevertheless, they encounter challenges, e.g., 1) Transformers require substantial computational resources, and 2) these layers are carefully assembled and designed. Recently, large kernel convolutional neural networks (LKCNNs) show excellent performance in natural visual tasks. To tackle these limitations and explore the capability of LKCNNs for HSI classification, we present a novel simple and powerful multi-scale large kernel convolutional neural network architecture (MSLKCNN) with the largest kernel size as large as 15 × 15, in contrast to commonly used 3 × 3, for HSI classification. MSLKCNN avoids these specialized designs, comprising a noise suppression module (NSM) and a multi-scale large kernel convolution (MSLKC). Specifically, NSM is first used to suppress the noise and reduce the number of the bands before extracting the features. Then, MSLKC, as the only feature extraction layer of MSLKCNN, joints three parallel convolutions to capture the features of various types (i.e. spectral, spectral-spatial) and ranges (i.e., small local, larger local, and global) from the dimension of scale: (C1) convolution with a kernel size of 1 × 1 is used to extract spectral features; (C2) multi-scale large kernel depthwise separable convolution (MLKDC) is proposed to learn the spectral-spatial features of different ranges including short-range, middle-range, and long-range; and (C3) multi-scale dilated depthwise separable convolution (MDDC) is designed to aggregate the spectral-spatial features between land covers at various distances. Extensive experimental results on three public HSI datasets demonstrate the competitiveness of the proposed MSLKCNN compared with several state-of-the-art methods.

Citation

LIU, X., NG, A.H.-M., LEI, F., REN, J. GUO, L. and DU, Z. [2025]. MSLKCNN: a simple and powerful multi-scale large kernel CNN for hyperspectral image classification. IEEE transactions on geoscience and remote sensing [online], Early Access. Available from: https://doi.org/10.1109/TGRS.2025.3566616

• Journal Article Type: Article
• Acceptance Date: May 2, 2025
• Online Publication Date: May 2, 2025
• Deposit Date: May 8, 2025
• Publicly Available Date: May 8, 2025
• Journal: IEEE transactions on geoscience and remote sensing
• Print ISSN: 0196-2892
• Electronic ISSN: 1558-0644
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1109/tgrs.2025.3566616
• Keywords: Hyperspectral image (HSI) classification; Convolutional neural network (CNN); Multi-scale convolution; Large kernel convolution
• Public URL: https://rgu-repository.worktribe.com/output/2830252