← Zur Forschung

Forschung & Publikationen

ArcFace

Additive Angular Margin Loss for Deep Face Recognition

ArcFace introduced a simple but highly effective angular margin objective that made face embeddings more discriminative at production scale.

Paper-Details

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

Veröffentlichung

CVPR 2019

Autor:innen

Jiankang Deng, Jia Guo, Niannan Xue, Stefanos Zafeiriou

Paper öffnen

Forschungsüberblick

ArcFace became one of the most influential face recognition papers because it improves how identity classes are separated in embedding space while keeping training practical. The method is widely used as a strong baseline for verification, identification, search, and account security pipelines.

Produktive Einsatzszenarien

  • Identity verification and digital onboarding
  • Access control and workforce authentication
  • Duplicate account detection and fraud reduction
  • Large-scale face search and watchlist matching

Kernbeiträge

Adds an explicit angular margin so the model learns tighter same-person clusters and clearer separation between identities.

Improved benchmark performance on major face recognition evaluations helped establish ArcFace as a standard loss for modern face embeddings.

Works naturally with large-scale recognition systems that need stable similarity scores for matching, deduplication, and watchlist search.

Geschäftlicher Kontakt

Sprechen wir über Ihre geschäftlichen Anforderungen

Kontaktieren Sie InsightFace für Modelllizenzierung, Unterstützung bei Enterprise-Deployments, kundenspezifische KI-Entwicklung oder strategische Partnerschaften.

Wir akzeptieren ausschließlich Anfragen von geschäftlichen E-Mail-Adressen.