EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Domain Feature Alignment for Face Anti-Spoofing

Shizhe Zhang iD, Wenhui Nie

Sensors · 18.04.2023 · 23 (8) · 4077

DOI: 10.3390/s23084077 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.04.2023. Verfasst von Shizhe Zhang und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Face anti-spoofing is critical for enhancing the robustness of face recognition systems against presentation attacks. Existing methods predominantly rely on binary classification tasks. Recently, methods based on domain generalization have yielded promising results. However, due to distribution discrepancies between various domains, the differences in the feature space related to the domain considerably hinder the generalization of features from unfamiliar domains. In this work, we propose a multi-domain feature alignment framework (MADG) that addresses poor generalization when multiple source domains are distributed in the scattered feature space. Specifically, an adversarial learning process is designed to narrow the differences between domains, achieving the effect of aligning the features of multiple sources, thus resulting in multi-domain alignment. Moreover, to further improve the effectiveness of our proposed framework, we incorporate multi-directional triplet loss to achieve a higher degree of separation in the feature space between fake and real faces. To evaluate the performance of our method, we conducted extensive experiments on several public datasets. The results demonstrate that our proposed approach outperforms current state-of-the-art methods, thereby validating its effectiveness in face anti-spoofing.

Schlagwörter

Stichwörter der Autor:innen

domain generalizationface anti-spoofingfeature alignmentmulti-domain feature alignment domain generalization (MADG)multiple source domaintransfer learning

Autor:innen und Institutionen

  • School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China.

ORCID-Profile: Shizhe Zhang

Zitieren

APA

Zhang, S., & Nie, W. (2023). Multi-Domain Feature Alignment for Face Anti-Spoofing. Sensors, 23(8), 4077. https://doi.org/10.3390/s23084077

Vancouver

Zhang S, Nie W. Multi-Domain Feature Alignment for Face Anti-Spoofing. Sensors. 2023;23(8):4077. doi:10.3390/s23084077

BibTeX
@article{Zhang2023,
  author = {Zhang, Shizhe and Nie, Wenhui},
  title = {Multi-Domain Feature Alignment for Face Anti-Spoofing},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {8},
  pages = {4077},
  doi = {10.3390/s23084077}
}
Kostenlos starten →