arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2110.00337cs.CVcs.LG
收藏

PhiNets:边缘低功耗AI的可扩展骨干网

PhiNets: a scalable backbone for low-power AI at the edge

Fondazione Bruno Kessler (FBK)(布鲁诺·凯斯勒基金会)

Francesco Paissan, Alberto Ancilotto, Elisabetta Farella

摘要:

在物联网时代,我们看到许多互联和异构的移动和固定智能设备,将智能从云端分发到边缘已成为必要。由于有限的计算和通信能力、低存储器和有限的能量预算,将人工智能算法带到外围设备(例如传感器网络的端节点)是一项具有挑战性的任务,并且需要设计创新的方法。在这项工作中,我们提出了PhiNets,这是一种新的可扩展骨干,针对资源受限平台上基于深度学习的图像处理进行了优化。PhiNet基于专门设计的反向残差块,用于解耦计算成本,工作内存和参数内存,从而利用所有可用资源。通过YoloV2检测头和简单的在线和实时跟踪,所提出的架构在(i)COCO和VOC 2012基准上的检测以及(ii)MOT15基准上的跟踪方面取得了最先进的结果。PhiNets相对于以前最先进的模型(EfficientNetv1,MobileNetv2)减少了87%至93%的参数计数,并以更低的计算成本实现了更好的性能。此外,我们展示了我们的方法的原型节点的基础上的STM32H743微控制器(MCU)与2MB的内部闪存和1MB的RAM,并实现功率要求在10 mW的顺序。PhiNet的代码在GitHub上公开。

英文摘要:

In the Internet of Things era, where we see many interconnected and heterogeneous mobile and fixed smart devices, distributing the intelligence from the cloud to the edge has become a necessity. Due to limited computational and communication capabilities, low memory and limited energy budget, bringing artificial intelligence algorithms to peripheral devices, such as the end-nodes of a sensor network, is a challenging task and requires the design of innovative methods. In this work, we present PhiNets, a new scalable backbone optimized for deep-learning-based image processing on resource-constrained platforms. PhiNets are based on inverted residual blocks specifically designed to decouple the computational cost, working memory, and parameter memory, thus exploiting all the available resources. With a YoloV2 detection head and Simple Online and Realtime Tracking, the proposed architecture has achieved the state-of-the-art results in (i) detection on the COCO and VOC2012 benchmarks, and (ii) tracking on the MOT15 benchmark. PhiNets reduce the parameter count of 87% to 93% with respect to previous state-of-the-art models (EfficientNetv1, MobileNetv2) and achieve better performance with lower computational cost. Moreover, we demonstrate our approach on a prototype node based on a STM32H743 microcontroller (MCU) with 2MB of internal Flash and 1MB of RAM and achieve power requirements in the order of 10 mW. The code for the PhiNets is publicly available on GitHub.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑