Scholarlink

The deployment of deep learning models for face detection in edge devices presents challenges related to computational demands, resource constraints, and security. This paper will tackle the optimization for the distribution of face detection with different trained models to various hardware capabilities with the implementation of 4 secure communication protocols. To validate our proposal, we perform matrix evaluations across different NVIDIA edge devices and GPU-enabled PCs (GTX 1070Ti and RTX 2070), measuring performance metrics such as latency, throughput, and resource usage. The results demonstrate that our framework effectively balances accuracy, speed, and efficiency, providing optimal model-protocol combinations for edge devices.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Intelligent Secure Framework for Face Detection Distribution and Quantization Optimization on Edge Devices

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Nga Ly-Tu,
  • Xuan-Phuc Phan-Nguyen,
  • Nghia Truong-Hieu,
  • Son Nguyen-Tien,
  • Thao-Nguyen Thi-Thanh,
  • Tien Trinh-Thuy

摘要

The deployment of deep learning models for face detection in edge devices presents challenges related to computational demands, resource constraints, and security. This paper will tackle the optimization for the distribution of face detection with different trained models to various hardware capabilities with the implementation of 4 secure communication protocols. To validate our proposal, we perform matrix evaluations across different NVIDIA edge devices and GPU-enabled PCs (GTX 1070Ti and RTX 2070), measuring performance metrics such as latency, throughput, and resource usage. The results demonstrate that our framework effectively balances accuracy, speed, and efficiency, providing optimal model-protocol combinations for edge devices.