EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Superpixel-Tokenized and Frequency-Modulated Hybrid CNN–Transformer for Remote Sensing Semantic Segmentation

Xinlin Xie, Chenhao Chang, Yunyun Yang, Gang Xie

Remote Sensing · 02.03.2026 · 18 (5) · 754

DOI: 10.3390/rs18050754 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 02.03.2026. Verfasst von Xinlin Xie und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Research and Development Plan of Shanxi Province, Fundamental Research Program of Shanxi Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing semantic segmentation is fundamental for fine-grained urban scene understanding, which in turn provides pixel-level semantic insights for urban development and environmental surveillance. However, existing hybrid segmentation architectures fail to incorporate intrinsic geometric and physical priors, inevitably leading to structural fragmentation, boundary ambiguity, and spatial misalignment of heterogeneous features. Therefore, we propose a Superpixel-Tokenized and Frequency-Modulated Hybrid CNN–Transformer network (SFCT-Net) for remote sensing semantic segmentation. The proposed network integrates superpixel tokens and high-frequency constraints to preserve structural integrity and boundary precision. First, our Superpixel-Tokenized Linear Position Attention (STLPA) module replaces rigid window tokens with semantic superpixels to ensure object integrity with linear computational complexity. Second, we construct a Frequency-Modulated Deformable Edge Refinement (FMDER) module that leverages high-frequency spectral priors to modulate deformable sampling, achieving robust boundary recovery. Finally, we develop the Spatial–Semantic Feature Coupling (SSFC) module, which employs a dual-branch strategy to correct spatial drift and align deep semantic features with shallow details. Experiments conducted on our self-built Taiyuan Satellite Remote Sensing Dataset (TSRSD) along with the ISPRS Vaihingen and Potsdam benchmark datasets demonstrate that our proposed SFCT-Net delivers state-of-the-art performance and efficiency by fusing superpixel and frequency priors for robust structural and boundary recovery.

Förderung

  • National Natural Science Foundation of China
  • Key Research and Development Plan of Shanxi Province
  • Fundamental Research Program of Shanxi Province
  • Foundation of Shanxi Key Laboratory Of Advanced Control and Industrial Intelligence

Zitieren

APA

Xie, X., Chang, C., Yang, Y., & Xie, G. (2026). Superpixel-Tokenized and Frequency-Modulated Hybrid CNN–Transformer for Remote Sensing Semantic Segmentation. Remote Sensing, 18(5), 754. https://doi.org/10.3390/rs18050754

Vancouver

Xie X, Chang C, Yang Y, Xie G. Superpixel-Tokenized and Frequency-Modulated Hybrid CNN–Transformer for Remote Sensing Semantic Segmentation. Remote Sensing. 2026;18(5):754. doi:10.3390/rs18050754

BibTeX
@article{Xie2026,
  author = {Xie, Xinlin and Chang, Chenhao and Yang, Yunyun and Xie, Gang},
  title = {Superpixel-Tokenized and Frequency-Modulated Hybrid CNN–Transformer for Remote Sensing Semantic Segmentation},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {5},
  pages = {754},
  doi = {10.3390/rs18050754}
}
Kostenlos starten →