研究与发表
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.
论文信息
SCRFD: Sample and Computation Redistribution for Efficient Face Detection
发表渠道
ICLR 2022
作者
Jia Guo, Jiankang Deng, Alexandros Lattas, Stefanos Zafeiriou
研究概览
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.
落地应用
- 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
核心贡献
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.