Xun Liu
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
Authors
Alex Hay-Man Ng
Fangyuan Lei
Professor Jinchang Ren j.ren@rgu.ac.uk
Professor of Computing Science
Li Guo
Zheyuan Du
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 |
Files
LIU 2025 MSLKCNN (AAM)
(7.7 Mb)
PDF
Publisher Licence URL
https://creativecommons.org/licenses/by/4.0/
Copyright Statement
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
You might also like
Two-click based fast small object annotation in remote sensing images.
(2024)
Journal Article
Prompting-to-distill semantic knowledge for few-shot learning.
(2024)
Journal Article
Detection-driven exposure-correction network for nighttime drone-view object detection.
(2024)
Journal Article
Feature aggregation and region-aware learning for detection of splicing forgery.
(2024)
Journal Article
Downloadable Citations
About OpenAIR@RGU
Administrator e-mail: publications@rgu.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2025
Advanced Search