MSCD-Net : From Unimodal to Multimodal Semantic Change Detection

Wang, Jian and Xie, Hong and Yan, Li and Zhou, Tingyuan and Wang, Yanheng and Zhang, Jing and Bruzzone, Lorenzo and Atkinson, Peter M. (2025) MSCD-Net : From Unimodal to Multimodal Semantic Change Detection. IEEE Transactions on Geoscience and Remote Sensing, 63: 4508017. pp. 1-17. ISSN 0196-2892

Text (FINAL VERSION)
FINAL_VERSION.pdf - Accepted Version
Available under License Creative Commons Attribution.
Download (26MB)

Abstract

Semantic change detection (SCD) involves temporal changes and spatial semantics. Its working principle and processing flow usually include land semantic segmentation (LSS) and binary change detection (BCD). Due to its significant impact and practical value, SCD has received consistently wide attention in Earth observation. Nowadays, remote sensing data in various modalities are proliferating, calling for an urgent need to develop intelligent algorithms for multimodal remote sensing data. However, no efficient multimodal SCD methods exist currently. To address this limitation, this work proposes the first deep learning-based multimodal SCD method: MSCD-Net. MSCD-Net extracts multi-scale semantic and difference features after fusing multimodal features, and then aggregates and refines these features to output high-quality semantic segmentation and change maps. Additionally, a semantic difference decoder (SDD) module is designed to model semantic and difference features jointly. It can be integrated with existing methods to increase accuracy. Experimental results demonstrate that MSCD-Net achieves state-of-the-art performance on both multimodal and unimodal SCD datasets, and SDD has strong feature learning ability and compatibility. These findings imply that MSCD-Net is expected to promote the development and application of multimodal SCD.