EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semi-Supervised Change Detection for High-Resolution Remote Sensing Images Based on Label Extension

Shuo Liu, Li Wan, Fei Xie, Xinlong Shu, Yaxin Lei, Wuxia Zhang

Remote Sensing · 29.05.2026 · 18 (11) · 1746

DOI: 10.3390/rs18111746 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 29.05.2026. Verfasst von Shuo Liu und 5 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Southwest China Artificial Weather Modification Capability Construction, Shaanxi Provincial Department of Education.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Change detection (CD) refers to the analysis of changes in the utilization of land, buildings, and other targets in the same surface environment using relevant technologies and remote sensing images. Although deep learning-based change detection methods have achieved excellent results, they remain highly dependent on extensive labeled data. High-resolution remote sensing imagery typically encompasses an abundance of details and a greater quantity of pixels compared to low-resolution datasets. Therefore, data annotation costs are significantly higher. Currently, within the context of semi-supervised change detection (SSCD) driven by consistency learning, pseudo-labels are usually selected only by threshold screening, but this ignores the spatial relationships among pixels and does not fully utilize unlabeled data, thereby affecting the model’s performance. Consequently, we propose a semi-supervised high-resolution remote sensing image change detection method based on label expansion. First, a “one weak, two strong” (OW-TS) consistency regularization (CR) framework is introduced to constrain the overall consistency between the prediction results of weak and strong augmentations, as well as between the two strong augmentations. At the same time, the location interaction map (LIM) is introduced to utilize the global–local relationship between pixels and mine the consistency of pseudo-labels, thereby improving the model’s accuracy. Empirical findings indicate that when the model is trained utilizing 20% labeled data and 80% unlabeled data on the LEVIR-CD dataset, the IoUc index reaches 83.38%. The model performs well in smoothing the boundary between changed and unchanged areas and is comparable in performance to some fully supervised methods.

Förderung

  • National Natural Science Foundation of China
  • Southwest China Artificial Weather Modification Capability Construction
  • Shaanxi Provincial Department of Education
  • Chengdu Key Research and Development Program

Zitieren

APA

Liu, S., Wan, L., Xie, F., Shu, X., Lei, Y., & Zhang, W. (2026). Semi-Supervised Change Detection for High-Resolution Remote Sensing Images Based on Label Extension. Remote Sensing, 18(11), 1746. https://doi.org/10.3390/rs18111746

Vancouver

Liu S, Wan L, Xie F, Shu X, Lei Y, Zhang W. Semi-Supervised Change Detection for High-Resolution Remote Sensing Images Based on Label Extension. Remote Sensing. 2026;18(11):1746. doi:10.3390/rs18111746

BibTeX
@article{Liu2026,
  author = {Liu, Shuo and Wan, Li and Xie, Fei and Shu, Xinlong and Lei, Yaxin and Zhang, Wuxia},
  title = {Semi-Supervised Change Detection for High-Resolution Remote Sensing Images Based on Label Extension},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {11},
  pages = {1746},
  doi = {10.3390/rs18111746}
}
Kostenlos starten →