Software Optimization and Design Methodology for Low Power Computer Vision Systems

Author:

Ha Soonhoi1ORCID,Jeong EunJin1ORCID

Affiliation:

1. Computer Science and Engineering, Seoul National University, Seoul, Korea (the Republic of)

Abstract

This tutorial paper addresses a low power computer vision system as an example of a growing application domain of neural networks, exploring various technologies developed to enhance accuracy within the resource and performance constraints imposed by the hardware platform. Focused on a given hardware platform and network model, software optimization techniques, including pruning, quantization, low-rank approximation, and parallelization, aim to satisfy resource and performance constraints while minimizing accuracy loss. Due to the interdependence of model compression approaches, their systematic application is crucial, as evidenced by winning solutions in the Lower Power Image Recognition Challenge (LPIRC) of 2017 and 2018. Recognizing the typical heterogeneity of processing elements in contemporary hardware platforms, the effective utilization through parallelizing neural networks emerges as increasingly vital for performance enhancement. The paper advocates for a more impactful strategy—designing a network architecture tailored to a specific hardware platform. For detailed information on each technique, the paper provides corresponding references.

Publisher

Association for Computing Machinery (ACM)

Reference38 articles.

1. Enabling mixed-precision quantized neural networks in extreme-edge devices

2. Krishna Teja Chitty-Venkata Sparsh Mittal Murali Emani Venkatram Vishwanath and Arun K. Somani. 2023. A Survey of Techniques for Optimizing Transformer Inference. In arXiv:2307.07982 [cs.LG].

3. Matthieu Courbariaux and Yoshua Bengio. 2016. BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1. CoRR abs/1602.02830(2016). arXiv:1602.02830 http://arxiv.org/abs/1602.02830

4. Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In arXiv:2010.11929 [cs.CV].

5. Jonathan Frankle and Michael Carbin. 2019. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks. In Proceedings of the 7th International Conference on Learning Representations (ICLR’19).

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3