EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DFST-UNet: Dual-Domain Fusion Swin Transformer U-Net for Image Forgery Localization

Jianhua Yang, Anjun Xie, Tao Mai, Yifang Chen iD

Entropy · 17.05.2025 · 27 (5) · 535

DOI: 10.3390/e27050535 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 17.05.2025. Verfasst von Jianhua Yang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Cyber Security, Guangdong Polytechnic Normal University, Guangzhou 510630, China. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, the Basic and Applied Basic Research Foundation of Guangdong Province, the Opening Project of Guangdong Provincial Key Laboratory of Information Security Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image forgery localization is critical in defending against the malicious manipulation of image content, and is attracting increasing attention worldwide. In this paper, we propose a Dual-domain Fusion Swin Transformer U-Net (DFST-UNet) for image forgery localization. DFST-UNet is built on a U-shaped encoder–decoder architecture. Swin Transformer blocks are integrated into the U-Net architecture to capture long-range context information and perceive forged regions at different scales. Considering the fact that high-frequency forgery information is an essential clue for forgery localization, a dual-stream encoder is proposed to comprehensively expose forgery clues in both the RGB domain and the frequency domain. A novel high-frequency feature extractor module (HFEM) is designed to extract robust high-frequency features. A hierarchical attention fusion module (HAFM) is designed to effectively fuse the dual-domain features. Extensive experimental results demonstrate the superiority of DFST-UNet over the state-of-the-art methods in the task of image forgery localization.

Schlagwörter

Stichwörter der Autor:innen

dual-domain fusionimage forensicsimage forgery localizationswin transformer

Autor:innen und Institutionen

  • School of Cyber Security, Guangdong Polytechnic Normal University, Guangzhou 510630, China.

ORCID-Profile: Yifang Chen

Förderung

  • National Natural Science Foundation of China
  • the Basic and Applied Basic Research Foundation of Guangdong Province
  • the Opening Project of Guangdong Provincial Key Laboratory of Information Security Technology
  • Key Research Platforms and Projects of Universities in Guangdong Province
  • Research Project of Guangdong Polytechnic Normal University
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Opening Project of Guangdong Provincial Key Laboratory of Information Security Technology

Zitieren

APA

Yang, J., Xie, A., Mai, T., & Chen, Y. (2025). DFST-UNet: Dual-Domain Fusion Swin Transformer U-Net for Image Forgery Localization. Entropy, 27(5), 535. https://doi.org/10.3390/e27050535

Vancouver

Yang J, Xie A, Mai T, Chen Y. DFST-UNet: Dual-Domain Fusion Swin Transformer U-Net for Image Forgery Localization. Entropy. 2025;27(5):535. doi:10.3390/e27050535

BibTeX
@article{Yang2025,
  author = {Yang, Jianhua and Xie, Anjun and Mai, Tao and Chen, Yifang},
  title = {DFST-UNet: Dual-Domain Fusion Swin Transformer U-Net for Image Forgery Localization},
  journal = {Entropy},
  year = {2025},
  volume = {27},
  number = {5},
  pages = {535},
  doi = {10.3390/e27050535}
}
Kostenlos starten →