BriefGPT.xyz
Jul, 2023
Grad-FEC:协同智能中的深度特征不等误差保护
Grad-FEC: Unequal Loss Protection of Deep Features in Collaborative Intelligence
HTML
PDF
Korcan Uyanik, S. Faegheh Yeganli, Ivan V. Bajić
TL;DR
本文介绍了一种新方法——不等误差保护（ULP），通过特征重要性估算器来选择性应用前向纠错（FEC）码以保护重要的数据包以提高协同智能系统的鲁棒性和可靠性。
Abstract
collaborative intelligence
(CI) involves dividing an artificial intelligence (AI) model into two parts: front-end, to be deployed on an edge device, and back-end, to be deployed in the cloud. The
deep feature tensors
→