Two-stage transfer learning for airborne multi-spectral image classifiers

Rise, B ORCID: 0009-0002-0211-5883, Uney, M ORCID: 0000-0001-6561-0406 and Huang, X ORCID: 0000-0001-6267-0366 (2026) Two-stage transfer learning for airborne multi-spectral image classifiers Signal Processing, 240. p. 110358. ISSN 0165-1684, 1872-7557

Access the full-text of this item by clicking on the Open Access link.

Abstract

In this work, we propose a novel training paradigm designed to support transfer learning for more effective classification in multispectral airborne imagery. Current state-of-the-art approaches typically rely on either leveraging solely RGB (red-green-blue) pretraining or applying in-domain transfer learning for multispectral imagery classification. Instead, our approach constructs and trains two separate neural network models (backbones): one specifically for wavelengths with available pretrained data (like visible bands) and another trained from scratch on all-bands available in the dataset. These models are then integrated with a fully-connected layer or multi-layered perceptron, which is trained on the features from both networks. This allows us to exploit the significant benefits of generalizable features learned from RGB datasets and the information provided by the full spectrum of multispectral bands. We employ the BigEarthNet and EuroSAT datasets, encompassing Sentinel-2 satellite imagery in the visual and infrared bands. This approach yields considerable performance gains in comparison with other training strategies across every evaluation metric we utilized for these datasets. The results are also consistent across a variety of backbone architectures, underlining the efficacy of our transfer learning technique in the analysis of multispectral data.

Item Type:	Article
Uncontrolled Keywords:	Multispectral imagery, Remote sensing, Deep learning, Transfer learning, Scene classification
Divisions:	Faculty of Science & Engineering Faculty of Science & Engineering > School of Engineering Faculty of Science & Engineering > School of Engineering > Electrical Engineering and Electronics Faculty of Science & Engineering > School of Computer Science & Informatics Faculty of Science & Engineering > School of Computer Science & Informatics > Artificial Intelligence
Depositing User:	Symplectic Admin
Date Deposited:	20 Nov 2025 15:27
Last Modified:	10 Mar 2026 00:20
DOI:	10.1016/j.sigpro.2025.110358
Open Access URL:	https://doi.org/10.1016/j.sigpro.2025.110358
Related Websites:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3195542
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.