MDDNet: multilevel difference-enhanced denoise network for unsupervised change detection in SAR images.

Zong, He; Zhang, Erlei; Li, Xinyu; Zhang, Hongming; Ren, Jinchang

Abstract

Change detection in synthetic aperture radar (SAR) images is a hot yet highly challenging task in remote sensing. Existing unsupervised SAR change detection methods often struggle with inherent speckle noise and insufficiently utilize pseudo-labels, particularly neglecting uncertain areas. In this paper, we propose a multilevel difference-enhanced denoise dual-branch network (MDDNet), comprising representation learning and change detection branches. First, fuzzy c-means clustering is employed to generate pseudo-labels, categorizing the image areas as changed, nochanged, and uncertain. Second, we design a denoise representation loss function in the representation learning branch to maximize the use of pseudo-labels, while mitigating speckle noise. Furthermore, a multilevel difference computation module is proposed to focus on changes in ground objects and capture more comprehensive change information. Experimental results on three public SAR datasets show that the proposed method outperforms six state-of-the-art methods, achieving the best performance with an average overall accuracy of 98.86% and an average Kappa coefficient of 89.36%.

Citation

ZONG, H., ZHANG, E., LI, X., ZHANG, H. and REN, J. 2025. MDDNet: multilevel difference-enhanced denoise network for unsupervised change detection in SAR images. In Proceedings of the 50th IEEE (Institute of Electrical and Electronics Engineers) International conference on acoustics, speech and signal processing 2025 (ICASSP 2025), 06-11 April 2025, Hyderabad, India. Piscataway: IEEE [online], article number 576. Available from: https://doi.org/10.1109/icassp49660.2025.10887943

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 50th IEEE (Institute of Electrical and Electronics Engineers) International conference on acoustics, speech and signal processing 2025 (ICASSP 2025)
• Start Date: Apr 6, 2025
• End Date: Apr 11, 2025
• Acceptance Date: Dec 18, 2024
• Online Publication Date: Mar 7, 2025
• Publication Date: Apr 6, 2025
• Deposit Date: Mar 17, 2025
• Publicly Available Date: Mar 17, 2025
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Article Number: 576
• Series ISSN: 2379-190X
• ISBN: 9798350368741
• DOI: https://doi.org/10.1109/icassp49660.2025.10887943
• Keywords: Change detection; Denoise representation; Multilevel difference computation; Synthetic aperture radar (SAR) images
• Public URL: https://rgu-repository.worktribe.com/output/2755036