← Назад к исследованиям

Исследования и Публикации

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.

Сведения о статье

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

Публикация

CVPR 2019

Авторы

Jiankang Deng, Jia Guo, Niannan Xue, Stefanos Zafeiriou

Открыть статью

Обзор исследования

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.

Сценарии применения

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

Ключевые преимущества

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.

Коммерческий контакт

Давайте обсудим ваши бизнес-задачи

Свяжитесь с InsightFace по вопросам лицензирования моделей, поддержки корпоративного внедрения, кастомной разработки ИИ или стратегического партнёрства.

Мы принимаем запросы только с корпоративных адресов электронной почты.