EUVIMEDEUVIMED entdecken
Crossref

FCL: frequency-based contrastive learning for generalizable face forgery detection

Yu Zhu, Shengze Wang, Yufeng Gu, Ziming Zhu, Nan Wang

Multimedia Systems · 2026-06 · 32 (4)

DOI: 10.1007/s00530-026-02325-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Multimedia Systems, online erschienen am 06.05.2026. Verfasst von Yu Zhu und 4 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the proliferation of deepfake techniques, face forgery detection has emerged as a critical area of research to mitigate the risks associated with facial manipulation. Recent studies have highlighted the superiority of frequency information over color-space input, especially in high-compression scenarios. However, most frequency-enhanced methods employ a two-stream network architecture, assigning separate encoders for RGB and frequency domains, and rely solely on vanilla binary cross-entropy loss, limiting their generalization ability. To address these limitations, we propose a novel framework, Frequency-enhanced Contrastive Learning (FCL), which trains the model in a supervised manner using contrastive loss. FCL treats two views of different modalities generated from the same image as positive pairs and samples with opposite labels as negative pairs. This approach pulls features from the RGB and high-frequency domains closer while pushing features of pristine and forgery faces apart. Additionally, we introduce a Shallow Feature Supplement (SFS) module to complement local information from low-level shallow feature embeddings into high-level feature maps, and a Dual Modal Fusion (DMF) module to adaptively aggregate information from both domains. Extensive experiments on seven datasets demonstrate that our method achieves competitive generalization performance against state-of-the-art competitors, with significant advantages in heavily compressed scenarios. FCL achieves an accuracy of 92.29% and an AUC of 94.25% on the heavily compressed FaceForensics++ (LQ, C40) dataset, which verifies its robustness against compression in practical application scenarios. The source code of our proposed algorithm is available at https://github.com/Y30230924Wang/Frequency-Enhanced-Contrastive-Learning.

Zitieren

APA

Zhu, Y., Wang, S., Gu, Y., Zhu, Z., & Wang, N. (2026). FCL: frequency-based contrastive learning for generalizable face forgery detection. Multimedia Systems, 32(4). https://doi.org/10.1007/s00530-026-02325-7

Vancouver

Zhu Y, Wang S, Gu Y, Zhu Z, Wang N. FCL: frequency-based contrastive learning for generalizable face forgery detection. Multimedia Systems. 2026;32(4). doi:10.1007/s00530-026-02325-7

BibTeX
@article{Zhu2026,
  author = {Zhu, Yu and Wang, Shengze and Gu, Yufeng and Zhu, Ziming and Wang, Nan},
  title = {FCL: frequency-based contrastive learning for generalizable face forgery detection},
  journal = {Multimedia Systems},
  year = {2026},
  volume = {32},
  number = {4},
  doi = {10.1007/s00530-026-02325-7}
}
Kostenlos starten →