Open Access

ARTICLE

MewCDNet: A Wavelet-Based Multi-Scale Interaction Network for Efficient Remote Sensing Building Change Detection

Jia Liu¹, Hao Chen¹, Hang Gu¹, Yushan Pan^2,3, Haoran Chen¹, Erlin Tian⁴, Min Huang⁴, Zuhe Li^1,*

1 School of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou, 450002, China
2 Department of Computing, Xi’an Jiaotong-Liverpool University, Suzhou, 215123, China
3 Department of Computer Science, University of Liverpool, Liverpool, L69 7ZX, UK
4 School of Software, Zhengzhou University of Light Industry, Zhengzhou, 450002, China

* Corresponding Author: Zuhe Li. Email:

Computers, Materials & Continua 2026, 86(1), 1-24. https://doi.org/10.32604/cmc.2025.068162

Received 22 May 2025; Accepted 05 August 2025; Issue published 10 November 2025

Abstract

Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning, disaster emergency response, and resource management. However, existing methods face challenges such as spectral similarity between buildings and backgrounds, sensor variations, and insufficient computational efficiency. To address these challenges, this paper proposes a novel Multi-scale Efficient Wavelet-based Change Detection Network (MewCDNet), which integrates the advantages of Convolutional Neural Networks and Transformers, balances computational costs, and achieves high-performance building change detection. The network employs EfficientNet-B4 as the backbone for hierarchical feature extraction, integrates multi-level feature maps through a multi-scale fusion strategy, and incorporates two key modules: Cross-temporal Difference Detection (CTDD) and Cross-scale Wavelet Refinement (CSWR). CTDD adopts a dual-branch architecture that combines pixel-wise differencing with semantic-aware Euclidean distance weighting to enhance the distinction between true changes and background noise. CSWR integrates Haar-based Discrete Wavelet Transform with multi-head cross-attention mechanisms, enabling cross-scale feature fusion while significantly improving edge localization and suppressing spurious changes. Extensive experiments on four benchmark datasets demonstrate MewCDNet’s superiority over comparison methods: achieving F1 scores of 91.54% on LEVIR, 93.70% on WHUCD, and 64.96% on S2Looking for building change detection. Furthermore, MewCDNet exhibits optimal performance on the multi-class·SYSU dataset (F1: 82.71%), highlighting its exceptional generalization capability.

---

Keywords

---