Convolution Smooth: A Post-Training Quantization Method for Convolutional Neural Networks

Convolutional neural network (CNN) quantization is an efficient model compression technique primarily used for accelerating inference and optimizing resources. However, existing methods often apply different quantization strategies to activations and weights, without considering their interplay. To...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongyuan Chen, Zhendao Wang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10955493/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850148378630946816
author Yongyuan Chen
Zhendao Wang
author_facet Yongyuan Chen
Zhendao Wang
author_sort Yongyuan Chen
collection DOAJ
description Convolutional neural network (CNN) quantization is an efficient model compression technique primarily used for accelerating inference and optimizing resources. However, existing methods often apply different quantization strategies to activations and weights, without considering their interplay. To address this issue, this paper proposes a new method called Convolution Smooth, which aims to balance the quantization difficulty of activations and weights. This method effectively mitigates the significant accuracy drop typically observed in activation quantization with traditional methods. By appropriately scaling the tensors, the method shifts quantization complexity from activations to weights, ensuring a reasonable distribution of quantization difficulty between activations and weights. Experimental results show that the proposed method is applicable to a wide range of network models and can be seamlessly integrated into multiple post-training quantization (PTQ) methods. Through tensor scaling and the fusion of factors, the network achieves significant accuracy improvements in most cases, particularly when there is a significant discrepancy between the activation values and weight quantization bit-widths. This study provides a new theoretical foundation and technical support for CNN quantization compression.
format Article
id doaj-art-19b51b8f59ff4ef8828e963fe95e71f1
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-19b51b8f59ff4ef8828e963fe95e71f12025-08-20T02:27:16ZengIEEEIEEE Access2169-35362025-01-0113647276473610.1109/ACCESS.2025.355895610955493Convolution Smooth: A Post-Training Quantization Method for Convolutional Neural NetworksYongyuan Chen0https://orcid.org/0009-0008-9813-5603Zhendao Wang1https://orcid.org/0009-0002-8504-9649Department of Electronic Science and Technology, School of Physics and Electronics, Hunan University, Changsha, ChinaDepartment of Electronic Science and Technology, School of Physics and Electronics, Hunan University, Changsha, ChinaConvolutional neural network (CNN) quantization is an efficient model compression technique primarily used for accelerating inference and optimizing resources. However, existing methods often apply different quantization strategies to activations and weights, without considering their interplay. To address this issue, this paper proposes a new method called Convolution Smooth, which aims to balance the quantization difficulty of activations and weights. This method effectively mitigates the significant accuracy drop typically observed in activation quantization with traditional methods. By appropriately scaling the tensors, the method shifts quantization complexity from activations to weights, ensuring a reasonable distribution of quantization difficulty between activations and weights. Experimental results show that the proposed method is applicable to a wide range of network models and can be seamlessly integrated into multiple post-training quantization (PTQ) methods. Through tensor scaling and the fusion of factors, the network achieves significant accuracy improvements in most cases, particularly when there is a significant discrepancy between the activation values and weight quantization bit-widths. This study provides a new theoretical foundation and technical support for CNN quantization compression.https://ieeexplore.ieee.org/document/10955493/Convolutional neural networkpost-training quantizationtensor scalingfactor fusion
spellingShingle Yongyuan Chen
Zhendao Wang
Convolution Smooth: A Post-Training Quantization Method for Convolutional Neural Networks
IEEE Access
Convolutional neural network
post-training quantization
tensor scaling
factor fusion
title Convolution Smooth: A Post-Training Quantization Method for Convolutional Neural Networks
title_full Convolution Smooth: A Post-Training Quantization Method for Convolutional Neural Networks
title_fullStr Convolution Smooth: A Post-Training Quantization Method for Convolutional Neural Networks
title_full_unstemmed Convolution Smooth: A Post-Training Quantization Method for Convolutional Neural Networks
title_short Convolution Smooth: A Post-Training Quantization Method for Convolutional Neural Networks
title_sort convolution smooth a post training quantization method for convolutional neural networks
topic Convolutional neural network
post-training quantization
tensor scaling
factor fusion
url https://ieeexplore.ieee.org/document/10955493/
work_keys_str_mv AT yongyuanchen convolutionsmoothaposttrainingquantizationmethodforconvolutionalneuralnetworks
AT zhendaowang convolutionsmoothaposttrainingquantizationmethodforconvolutionalneuralnetworks