Towards Network-accelerated ML-based Distributed Computer Vision Systems
Authors:
- 1 December 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 122-129
Abstract
Computer vision is a crucial component in many modern applications (e.g., medical image analysis, environmental monitoring and self-driving cars). However, their stringent computational, latency and bandwidth requirements still pose a huge challenge to system architects, which must seek for alternatives to both the limited resources (e.g., low-end CPU) on client devices and the hurdles of moving data from clients to cloud/edge servers for analysis. In this work, we advocate for the usage of emerging programmable network devices to speed up ML-based computer vision tasks, particularly image classification, on resource constrained environments. To take the first step towards this new paradigm, we propose NetPixel, a framework that enables P4-programmable switches to classify images in realtime, accurately and at scale. We implemented a prototype of NetPixel in a software switch to show its feasibility and conducted a preliminary evaluation on widely adopted datasets. Our results show that NetPixel can classify images with an accuracy within 8% that of a server-based implementation even for shallow classifiers and low-resolution images.Keywords
This publication has 27 references indexed in Scilit:
- CTCV: A protocol for Coordinated Transport of Correlated Video in Smart Camera Networks2016
- Edge Computing: Vision and ChallengesIEEE Internet of Things Journal, 2016
- The Promise of Edge ComputingComputer, 2016
- Forwarding metamorphosis2013
- Automated Classification of Bitmap Images using Decision TreesPolibits, 2011
- Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categoriesComputer Vision and Image Understanding, 2007
- A survey of image classification methods and techniques for improving classification performanceInternational Journal of Remote Sensing, 2007
- Bloom Filters in Probabilistic Verification2004
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- A survey of decision tree classifier methodologyIEEE Transactions on Systems, Man, and Cybernetics, 1991