Forschung & Publikationen
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.
Paper-Details
SCRFD: Sample and Computation Redistribution for Efficient Face Detection
Veröffentlichung
ICLR 2022
Autor:innen
Jia Guo, Jiankang Deng, Alexandros Lattas, Stefanos Zafeiriou
Forschungsüberblick
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.
Produktive Einsatzszenarien
- 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
Kernbeiträge
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.
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.