@inproceedings{f9a2685585314caca6fbe29b1dbd0390,
title = "Poster Abstract: E4: Energy-Efficient Early-Exit DNN Inference Framework for Edge Video Analytics",
abstract = "Deep neural networks (DNNs) are becoming extremely popular in video analytics applications at the edge. However, compute-intensive DNNs pose new challenges to achieve energy-efficient DNN inference on resource-constrained edge devices. In this paper, we propose E4, an energy-efficient DNN inference framework for edge video analytics. First, E4 analyzes video frame complexity by employing an attention-based cascade module that automatically determines DNN exit points. Second, E4's just-in-time (JIT) profiler leverages coordinate descent search to co-optimize the CPU and GPU clock frequencies for each layer before the DNN exit point. Preliminary experimental results show that E4 outperforms exiting methods in terms of power consumption and inference latency.",
keywords = "DVFS, early-exit DNN, edge video analytics",
author = "Ziyang Zhang and Yang Zhao and Jie Liu",
note = "Publisher Copyright: {\textcopyright} 2023 Copyright is held by the owner/author(s). Publication rights licensed to ACM.; 21st ACM Conference on Embedded Networked Sensors Systems, SenSys 2023 ; Conference date: 13-11-2023 Through 15-11-2023",
year = "2024",
month = apr,
day = "26",
doi = "10.1145/3625687.3628383",
language = "英语",
series = "SenSys 2023 - Proceedings of the 21st ACM Conference on Embedded Networked Sensors Systems",
publisher = "Association for Computing Machinery, Inc",
pages = "512--513",
booktitle = "SenSys 2023 - Proceedings of the 21st ACM Conference on Embedded Networked Sensors Systems",
}