Recherche et Publications
SCRFD
Sample and Computation Redistribution for Efficient Face Detection
SCRFD is designed for strong face detection accuracy under strict latency and compute budgets across edge, mobile, and server deployments.
Détails de l’article
SCRFD: Sample and Computation Redistribution for Efficient Face Detection
Publication
ICLR 2022
Auteurs
Jia Guo, Jiankang Deng, Alexandros Lattas, Stefanos Zafeiriou
Vue d’ensemble de la recherche
SCRFD improves efficiency by redistributing both training emphasis and model computation so the detector spends budget where it matters most. The result is a family of detectors that balances accuracy and throughput well for production systems that need real-time or edge-friendly inference.
Applications en production
- Edge cameras, kiosks, and smart terminals
- On-device face detection for mobile AI apps
- High-throughput video preprocessing pipelines
- Server-side face localization before recognition or liveness analysis
Contributions clés
Redistributes samples and computation to improve the accuracy-speed tradeoff instead of simply scaling model size upward.
Supports multiple deployment tiers, helping teams choose a detector that matches mobile, embedded, desktop, or server constraints.
Delivers strong WIDER FACE performance while remaining practical for real-time inference pipelines.
Contact commercial
Parlons de vos besoins business
Contactez InsightFace pour les licences de modèles, le support de déploiement en entreprise, le développement IA sur mesure ou les partenariats stratégiques.
Nous n'acceptons que les demandes provenant d'adresses e-mail professionnelles.