EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

NF-SemiCD: semi-supervised remote sensing change detection with normalizing flows

Guitao Yu, Dongjie Zhang, Ye Zheng, Baochen Yao, Chengbin Peng

PeerJ Computer Science · 03.04.2026 · 12 · e3751

DOI: 10.7717/peerj-cs.3751 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 03.04.2026. Verfasst von Guitao Yu und 4 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Zhejiang Provincial Natural Science Foundation of China, Ningbo Science and Technology Innovation Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Change detection (CD) in remote sensing images has long been of great interest to researchers. Due to the substantial time and effort required for data annotation in remote sensing, semi-supervised methods have attracted extensive attention as a promising solution for achieving satisfactory performance under limited samples. However, existing semi-supervised approaches often encounter significant challenges, most notably class imbalance and subtle changes in feature distributions, making it difficult to distinguish changes from unchanged regions. Here, we propose a novel strategy, named NF-SemiCD, which incorporates normalizing flows in a semi-supervised architecture. We leverage normalizing flows to characterize the feature distribution of unchanged regions and derive a probability distribution model. Its sensitivity to changes in probability allows us to get a probability feature map, which provides useful information on deep difference features. To this end, we devise a three-stage training scheme: (1) training an encoder-decoder network with labeled data, (2) training a normalizing flow decoder on labeled data, and (3) training the encoder-decoder network with all data. Experiments on three benchmark datasets demonstrate that NF-SemiCD outperforms existing state-of-the-art methods, highlighting its potential for improved change detection under semi-supervised settings.

Förderung

  • National Natural Science Foundation of China
  • Zhejiang Provincial Natural Science Foundation of China
  • Ningbo Science and Technology Innovation Project

Zitieren

APA

Yu, G., Zhang, D., Zheng, Y., Yao, B., & Peng, C. (2026). NF-SemiCD: semi-supervised remote sensing change detection with normalizing flows. PeerJ Computer Science, 12, e3751. https://doi.org/10.7717/peerj-cs.3751

Vancouver

Yu G, Zhang D, Zheng Y, Yao B, Peng C. NF-SemiCD: semi-supervised remote sensing change detection with normalizing flows. PeerJ Computer Science. 2026;12:e3751. doi:10.7717/peerj-cs.3751

BibTeX
@article{Yu2026,
  author = {Yu, Guitao and Zhang, Dongjie and Zheng, Ye and Yao, Baochen and Peng, Chengbin},
  title = {NF-SemiCD: semi-supervised remote sensing change detection with normalizing flows},
  journal = {PeerJ Computer Science},
  year = {2026},
  volume = {12},
  pages = {e3751},
  doi = {10.7717/peerj-cs.3751}
}
Kostenlos starten →