EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Category-Guided Transformer for Semantic Segmentation of High-Resolution Remote Sensing Images

Yue Ni, Jiahang Liu, Hui Zhang, Weijian Chi, Ji Luan

Remote Sensing · 02.09.2025 · 17 (17) · 3054

DOI: 10.3390/rs17173054 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 02.09.2025. Verfasst von Yue Ni und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovative Talent Program of Jiangsu.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-resolution remote sensing images suffer from large intra-class variance, high inter-class similarity, and significant scale variations, leading to incomplete segmentation and imprecise boundaries. To address these challenges, Transformer-based methods, despite their strong global modeling capability, often suffer from feature confusion, weak detail representation, and high computational cost. Moreover, existing multi-scale fusion mechanisms are prone to semantic misalignment across levels, hindering effective information integration and reducing boundary clarity. To address these issues, a Category-Guided Transformer (CIGFormer) is proposed. Specifically, the Category-Information-Guided Transformer Module (CIGTM) integrates global and local branches: the global branch combines window-based self-attention (WSAM) and window adaptive pooling self-attention (WAPSAM), using class predictions to enhance global context modeling and reduce intra-class and inter-class confusion; the local branch extracts multi-scale structural features to refine semantic representation and boundaries. In addition, an Adaptive Wavelet Fusion Module (AWFM) is designed, which leverages wavelet decomposition and channel-spatial joint attention for dynamic multi-scale fusion while preserving structural details. Extensive experiments on the ISPRS Vaihingen and Potsdam datasets demonstrate that CIGFormer, with only 21.50 M parameters, achieves outstanding performance in small object recognition, boundary refinement, and complex scene parsing, showing strong potential for practical applications.

Förderung

  • Innovative Talent Program of Jiangsu

Zitieren

APA

Ni, Y., Liu, J., Zhang, H., Chi, W., & Luan, J. (2025). Category-Guided Transformer for Semantic Segmentation of High-Resolution Remote Sensing Images. Remote Sensing, 17(17), 3054. https://doi.org/10.3390/rs17173054

Vancouver

Ni Y, Liu J, Zhang H, Chi W, Luan J. Category-Guided Transformer for Semantic Segmentation of High-Resolution Remote Sensing Images. Remote Sensing. 2025;17(17):3054. doi:10.3390/rs17173054

BibTeX
@article{Ni2025,
  author = {Ni, Yue and Liu, Jiahang and Zhang, Hui and Chi, Weijian and Luan, Ji},
  title = {Category-Guided Transformer for Semantic Segmentation of High-Resolution Remote Sensing Images},
  journal = {Remote Sensing},
  year = {2025},
  volume = {17},
  number = {17},
  pages = {3054},
  doi = {10.3390/rs17173054}
}
Kostenlos starten →