English

Quantization of Deep Neural Networks for Accurate Edge Computing

Computer Vision and Pattern Recognition 2021-10-15 v2

Abstract

Deep neural networks (DNNs) have demonstrated their great potential in recent years, exceeding the per-formance of human experts in a wide range of applications. Due to their large sizes, however, compressiontechniques such as weight quantization and pruning are usually applied before they can be accommodated onthe edge. It is generally believed that quantization leads to performance degradation, and plenty of existingworks have explored quantization strategies aiming at minimum accuracy loss. In this paper, we argue thatquantization, which essentially imposes regularization on weight representations, can sometimes help toimprove accuracy. We conduct comprehensive experiments on three widely used applications: fully con-nected network (FCN) for biomedical image segmentation, convolutional neural network (CNN) for imageclassification on ImageNet, and recurrent neural network (RNN) for automatic speech recognition, and experi-mental results show that quantization can improve the accuracy by 1%, 1.95%, 4.23% on the three applicationsrespectively with 3.5x-6.4x memory reduction.

Keywords

Cite

@article{arxiv.2104.12046,
  title  = {Quantization of Deep Neural Networks for Accurate Edge Computing},
  author = {Wentao Chen and Hailong Qiu and Jian Zhuang and Chutong Zhang and Yu Hu and Qing Lu and Tianchen Wang and Yiyu Shi and Meiping Huang and Xiaowe Xu},
  journal= {arXiv preprint arXiv:2104.12046},
  year   = {2021}
}

Comments

11 pages, 3 figures, 10 tables, accepted by the ACM Journal on Emerging Technologies in Computing Systems (JETC)

R2 v1 2026-06-24T01:29:21.261Z