Adaptive Global Power-of-Two Ternary Quantization Algorithm Based on Unfixed Boundary Thresholds

Author:

Sui Xuefu1,Lv Qunbo12,Ke Changjun1,Li Mingshan1,Zhuang Mingjin1,Yu Haiyang1,Tan Zheng12

Affiliation:

1. Aerospace Information Research Institute, Chinese Academy of Sciences, No. 9 Dengzhuang South Road, Haidian District, Beijing 100094, China

2. Department of Key Laboratory of Computational Optical Imagine Technology, Chinese Academy of Sciences, No. 9 Dengzhuang South Road, Haidian District, Beijing 100094, China

Abstract

In the field of edge computing, quantizing convolutional neural networks (CNNs) using extremely low bit widths can significantly alleviate the associated storage and computational burdens in embedded hardware, thereby improving computational efficiency. However, such quantization also presents a challenge related to substantial decreases in detection accuracy. This paper proposes an innovative method, called Adaptive Global Power-of-Two Ternary Quantization Based on Unfixed Boundary Thresholds (APTQ). APTQ achieves adaptive quantization by quantizing each filter into two binary subfilters represented as power-of-two values, thereby addressing the accuracy degradation caused by a lack of expression ability of low-bit-width weight values and the contradiction between fixed quantization boundaries and the uneven actual weight distribution. It effectively reduces the accuracy loss while at the same time presenting strong hardware-friendly characteristics because of the power-of-two quantization. This paper extends the APTQ algorithm to propose the APQ quantization algorithm, which can adapt to arbitrary quantization bit widths. Furthermore, this paper designs dedicated edge deployment convolutional computation modules for the obtained quantized models. Through quantization comparison experiments with multiple commonly used CNN models utilized on the CIFAR10, CIFAR100, and Mini-ImageNet data sets, it is verified that the APTQ and APQ algorithms possess better accuracy performance than most state-of-the-art quantization algorithms and can achieve results with very low accuracy loss in certain CNNs (e.g., the accuracy loss of the APTQ ternary ResNet-56 model on CIFAR10 is 0.13%). The dedicated convolutional computation modules enable the corresponding quantized models to occupy fewer on-chip hardware resources in edge chips, thereby effectively improving computational efficiency. This adaptive CNN quantization method, combined with the power-of-two quantization results, strikes a balance between the quantization accuracy performance and deployment efficiency in embedded hardware. As such, valuable insights for the industrial edge computing domain can be gained.

Funder

Key Program Project of Science and Technology Innovation of the Chinese Academy of Sciences

Innovation Fund Program of the Chinese Academy of Sciences

Publisher

MDPI AG

Subject

Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry

Reference77 articles.

1. Yan, S.-R., Pirooznia, S., Heidari, A., Navimipour, N.J., and Unal, M. (2022). IEEE Transactions on Engineering Management, IEEE.

2. CNN-32DC: An Improved Radar-Based Drone Recognition System Based on Convolutional Neural Network;Garcia;ICT Express,2022

3. Saha, D., and De, S. (2022). Practical Self-Driving Cars: Survey of the State-of-the-Art. Preprints.

4. ChipNet: Real-Time LiDAR Processing for Drivable Region Segmentation on an FPGA;Lyu;IEEE Trans. Circuits Syst. I Regul. Pap.,2019

5. Edge Computing: Vision and Challenges;Shi;Internet Things J. IEEE,2016

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