EUVIMEDEUVIMED entdecken
Crossref

Frequency-Spatial Complementation: Unified Channel-Specific Style Attack for Cross-Domain Few-Shot Learning

Zhong Ji, Zhilong Wang, Xiyao Liu, Yunlong Yu, Yanwei Pang, Jungong Han

IEEE Transactions on Image Processing · 2025 · 34 · 2242-2253

DOI: 10.1109/tip.2025.3553781 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Zhong Ji und 5 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Postdoctoral Innovation Talents Support Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-Domain Few-Shot Learning (CD-FSL) addresses the challenges of recognizing targets with out-of-domain data when only a few instances are available. Many current CD-FSL approaches primarily focus on enhancing the generalization capabilities of models in spatial domain, which neglects the role of the frequency domain in domain generalization. To take advantage of frequency domain in processing global information, we propose a Frequency-Spatial Complementation (FSC) model, which combines frequency domain information with spatial domain information to learn domain-invariant information from attacked data style. Specifically, we design a Frequency and Spatial Fusion (FusionFS) module to enhance the ability of the model to capture style-related information. Besides, we propose two attack strategies, i.e., the Gradient-guided Unified Style Attack (GUSA) strategy and the Channel-specific Attack Intensity Calculation (CAIC) strategy, which conduct targeted attacks on different channels to provide more diversified style data during the training phase, especially in single-source domain scenarios where the source domain data style is homogeneous. Extensive experiments across eight target domains demonstrate that our method significantly improves the model's performance under various styles.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Postdoctoral Innovation Talents Support Program
  • China Postdoctoral Science Foundation
  • Natural Science Foundation of Liaoning Province
  • Fundamental Research Project of SIA

Zitieren

APA

Ji, Z., Wang, Z., Liu, X., Yu, Y., Pang, Y., & Han, J. (2025). Frequency-Spatial Complementation: Unified Channel-Specific Style Attack for Cross-Domain Few-Shot Learning. IEEE Transactions on Image Processing, 34, 2242-2253. https://doi.org/10.1109/tip.2025.3553781

Vancouver

Ji Z, Wang Z, Liu X, Yu Y, Pang Y, Han J. Frequency-Spatial Complementation: Unified Channel-Specific Style Attack for Cross-Domain Few-Shot Learning. IEEE Transactions on Image Processing. 2025;34:2242-2253. doi:10.1109/tip.2025.3553781

BibTeX
@article{Ji2025,
  author = {Ji, Zhong and Wang, Zhilong and Liu, Xiyao and Yu, Yunlong and Pang, Yanwei and Han, Jungong},
  title = {Frequency-Spatial Complementation: Unified Channel-Specific Style Attack for Cross-Domain Few-Shot Learning},
  journal = {IEEE Transactions on Image Processing},
  year = {2025},
  volume = {34},
  pages = {2242--2253},
  doi = {10.1109/tip.2025.3553781}
}
Kostenlos starten →