Siamese change detection based on information interaction and fusion network

Abstract Change detection is widely utilized across various domains, such as disaster monitoring, where it aids in identifying differences between images captured at different time intervals. However, current methods often lack constraints on intermediate features and fail to comprehensively model t...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanni Zhang, Lei Yang, Caigen Zhou, Jiachen Wen, Licai Zhu
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-15468-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333293098467328
author Yanni Zhang
Lei Yang
Caigen Zhou
Jiachen Wen
Licai Zhu
author_facet Yanni Zhang
Lei Yang
Caigen Zhou
Jiachen Wen
Licai Zhu
author_sort Yanni Zhang
collection DOAJ
description Abstract Change detection is widely utilized across various domains, such as disaster monitoring, where it aids in identifying differences between images captured at different time intervals. However, current methods often lack constraints on intermediate features and fail to comprehensively model the temporal relationships among these features. Additionally, they rely on simplistic fusion mechanisms, leading to suboptimal network performance. In this paper, we propose: (1) a Feature Information Interaction Module (FIIM) based on spatial attention to enhance semantic information; (2) a Feature Pair Fusion Module (FPFM) with dual-branch structure to model bi-temporal relationships; and (3) a Multi-Scale Supervision Method (MSSM) using contrastive learning to better constrain intermediate features. Comparative experiments conducted on the CDD and LEVIR-CD datasets demonstrate the superiority of our proposed network over existing state-of-the-art methods. Code repository: https://github.com/joyeuxni/SNIIF-Net .
format Article
id doaj-art-52d6bf6aaf5841f7b7d9b575f5c008b6
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-52d6bf6aaf5841f7b7d9b575f5c008b62025-08-20T03:45:56ZengNature PortfolioScientific Reports2045-23222025-08-0115111310.1038/s41598-025-15468-wSiamese change detection based on information interaction and fusion networkYanni Zhang0Lei Yang1Caigen Zhou2Jiachen Wen3Licai Zhu4School of Artificial Intelligence, Yancheng Teachers UniversitySchool of Artificial Intelligence, Yancheng Teachers UniversitySchool of Artificial Intelligence, Yancheng Teachers UniversitySchool of Artificial Intelligence, Yancheng Teachers UniversitySchool of Artificial Intelligence, Yancheng Teachers UniversityAbstract Change detection is widely utilized across various domains, such as disaster monitoring, where it aids in identifying differences between images captured at different time intervals. However, current methods often lack constraints on intermediate features and fail to comprehensively model the temporal relationships among these features. Additionally, they rely on simplistic fusion mechanisms, leading to suboptimal network performance. In this paper, we propose: (1) a Feature Information Interaction Module (FIIM) based on spatial attention to enhance semantic information; (2) a Feature Pair Fusion Module (FPFM) with dual-branch structure to model bi-temporal relationships; and (3) a Multi-Scale Supervision Method (MSSM) using contrastive learning to better constrain intermediate features. Comparative experiments conducted on the CDD and LEVIR-CD datasets demonstrate the superiority of our proposed network over existing state-of-the-art methods. Code repository: https://github.com/joyeuxni/SNIIF-Net .https://doi.org/10.1038/s41598-025-15468-wChange detectionInformation interactionFeature fusionContrastive learning
spellingShingle Yanni Zhang
Lei Yang
Caigen Zhou
Jiachen Wen
Licai Zhu
Siamese change detection based on information interaction and fusion network
Scientific Reports
Change detection
Information interaction
Feature fusion
Contrastive learning
title Siamese change detection based on information interaction and fusion network
title_full Siamese change detection based on information interaction and fusion network
title_fullStr Siamese change detection based on information interaction and fusion network
title_full_unstemmed Siamese change detection based on information interaction and fusion network
title_short Siamese change detection based on information interaction and fusion network
title_sort siamese change detection based on information interaction and fusion network
topic Change detection
Information interaction
Feature fusion
Contrastive learning
url https://doi.org/10.1038/s41598-025-15468-w
work_keys_str_mv AT yannizhang siamesechangedetectionbasedoninformationinteractionandfusionnetwork
AT leiyang siamesechangedetectionbasedoninformationinteractionandfusionnetwork
AT caigenzhou siamesechangedetectionbasedoninformationinteractionandfusionnetwork
AT jiachenwen siamesechangedetectionbasedoninformationinteractionandfusionnetwork
AT licaizhu siamesechangedetectionbasedoninformationinteractionandfusionnetwork