CNN pruning and quantization compression method for reconfigurable structures

doi:10.11772/j.issn.1001-9081.2025081055

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (9): 2732-2740.DOI: 10.11772/j.issn.1001-9081.2025081055

• Artificial intelligence • Previous Articles

CNN pruning and quantization compression method for reconfigurable structures

Yixin ZHANG¹, Lin JIANG²(), Yuancheng LI³, Chen JI³

^1.College of Electrical and Control Engineering，Xi’an University of Science and Technology，Xi’an Shaanxi 710600，China
^2.School of Information Science and Technology，Northwest University，Xi’an Shaanxi 710127，China
^3.College of Artificial Intelligence and Computer Science，Xi’an University of Science and Technology，Xi’an Shaanxi 710600，China

Received:2025-09-11 Revised:2025-11-17 Accepted:2025-11-20 Online:2025-12-01 Published:2026-09-10
Contact: Lin JIANG
About author:ZHANG Yixin， born in 1999， M. S. candidate. Her research interests include neural network model compression， reconfigurable computing.
JIANG Lin， born in 1970， Ph. D.， professor. His research interests include application specific integrated circuit design， computer architecture.
LI Yuancheng， born in 1981， Ph. D.， associate professor. His research interests include computer architecture， high-performance computing.
JI Chen， born in 2000， M. S. candidate. His research interests include neural network lightweighting.
Supported by:
National Science and Technology Major Program on “Next-Generation Artificial Intelligence”(2022ZD0119005);Natural Science Basic Research Program of Shaanxi Province(2025JC-YBMS-754)

面向可重构结构的CNN剪枝与量化压缩方法

张一心¹, 蒋林²(), 李远成³, 纪辰³

^1.西安科技大学电气与控制工程学院，西安 710600
^2.西北大学信息科学与技术学院，西安 710127
^3.西安科技大学人工智能与计算机学院，西安 710600

通讯作者: 蒋林
作者简介:张一心（1999—），女，河南周口人，硕士研究生，CCF会员，主要研究方向：神经网络模型压缩、可重构计算
蒋林（1970—），男，陕西杨凌人，教授，博士生导师，博士，主要研究方向：专用集成电路设计、计算机体系结构
李远成（1981—），男，河南开封人，副教授，博士，CCF会员，主要研究方向：计算机体系结构、高性能计算
纪辰（2000—），男，陕西咸阳人，硕士研究生，CCF会员，主要研究方向：神经网络轻量化。
基金资助:
新一代人工智能国家科技重大专项(2022ZD0119005);陕西省自然科学基础研究计划项目(2025JC-YBMS-754);陕西省自然科学基础研究计划项目(2024JC-YBMS-539)

Abstract

Abstract:

To address the problems of high memory access overhead， redundant computation， and limited efficient deployment caused by the large parameter size of Convolutional Neural Networks （CNNs）， a CNN pruning and quantization compression method for reconfigurable structures was proposed to integrate network structure characteristics and hardware deployment requirements， and to perform co-optimization from both pruning and quantization dimensions. First， a convolutional layer pruning strategy based on feature similarity was introduced， in which feature evaluation， cluster and grouping， similarity calculation， and redundancy removal were performed in turn to filter out low-contribution and redundant filters. Second， progressive threshold pruning was applied at the fully connected layers to compress redundant weights. Third， in the quantization part， layer sensitivity indices were constructed using Hessian traces， and the precision of each layer was assigned adaptively under a bit-width budget. Finally， combining the characteristics of reconfigurable structures， an optimized deployment scheme was designed. Experimental results on the CIFAR-10 dataset show that the proposed method achieves a compression ratio of 16.2x for VGG16， surpassing Automated deep neural network Pruning and Quantization framework （APQ）（13.9x）. Compared to the model using fixed 16-bit precision， the pruned VGG16 using the proposed deployment scheme on a self-reconfigurable and self-evolvable Artificial Intelligence （AI） chip has the inference latency reduced from 23.3 ms to 9.1 ms， achieving a 2.56x speedup. It can be seen that the proposed method reduces the storage and transmission costs while maintaining the classification accuracy， improving the deployment efficiency and computational performance on edge devices.

Key words: reconfigurable structure, Convolutional Neural Network (CNN), model compression, structured pruning, adaptive quantization, Artificial Intelligence (AI) chip

摘要：

针对卷积神经网络（CNN）参数量大导致访存开销大、计算冗余和高效部署受限等问题，提出一种面向可重构结构的CNN剪枝与量化压缩方法，结合网络结构特性与硬件部署需求，从剪枝与量化两个维度协同优化。首先，提出基于特征相似的卷积层剪枝策略，依次经过特征信息评估、聚类分组、相似度计算和冗余筛选，筛选低贡献及冗余滤波器；其次，在全连接层采用渐进式阈值剪枝压缩冗余权重；再次，在量化部分利用Hessian迹构建层敏感度指标，在位宽预算下自适应地分配各层精度；最后，结合可重构结构特性，提出优化部署方案。实验结果表明，在CIFAR-10数据集上，本文方法对VGG16实现了16.20倍的压缩比，相较于APQ（Automated deep neural network Pruning and Quantization framework）的13.90倍具备更高压缩比；与16 bit固定精度的模型相比，采用本文部署策略后，剪枝后的VGG16在自重构自演化人工智能（AI）芯片上的推理时延由23.3 ms降至9.1 ms，加速比达2.56倍。本文方法在保证分类准确率的同时降低了存储与传输开销，提升了边缘设备部署效率与计算性能。

关键词: 可重构结构, 卷积神经网络, 模型压缩, 结构化剪枝, 自适应量化, 人工智能芯片

CLC Number:

TN409

Yixin ZHANG, Lin JIANG, Yuancheng LI, Chen JI. CNN pruning and quantization compression method for reconfigurable structures[J]. Journal of Computer Applications, 2026, 46(9): 2732-2740.

张一心, 蒋林, 李远成, 纪辰. 面向可重构结构的CNN剪枝与量化压缩方法[J]. 《计算机应用》唯一官方网站, 2026, 46(9): 2732-2740.

Figures/Tables 16

References 26

[1]	Zhao X， Wang L， Zhang Y， et al. A review of convolutional neural networks in computer vision ［J］. Artificial Intelligence Review， 2024， 57（4）： No.99.
[2]	Maurício J， Domingues I， Bernardino J. Comparing vision transformers and convolutional neural networks for image classification： a literature review ［J］. Applied Sciences， 2023， 13（9）： No.5521.
[3]	Yang C B， Liu H Y. Stable low-rank cp decomposition for compression of convolutional neural networks based on sensitivity［J］. Applied Sciences， 2024， 14（4）： No.1491.
[4]	徐杰，郭立君，冯海，等. 轻量化的多尺度特征校准小目标检测网络［J］. 计算机应用， 2025， 45（）： 228-234.
	Xu Jie， Guo Lijun， Feng Hai， et al. Lightweight multi-scale feature calibrated small object detection network ［J］. Journal of Computer Applications， 2025， 45（）： 228-234.
[5]	He Y， Xiao L. Structured pruning for deep convolutional neural networks： a survey ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2024， 46（5）： 2900-2919.
[6]	Liu W， Zhang M， Shi C， et al. Deep convolutional neural network compression method： tensor ring decomposition with variational Bayesian approach ［J］. Neural Processing Letters， 2024， 56（2）： No.103.
[7]	Nakata K， Miyashita D， Deguchi J， et al. Accelerating CNN inference with an adaptive quantization method using computational complexity-aware regularization ［J］. IEICE Transactions on Fundamentals of Electronics， Communications and Computer Sciences， 2025， E108-A（2）： 149-159.
[8]	Liu D， Zhu Y， Liu Z， et al. A survey of model compression techniques： past， present， and future ［J］. Frontiers in Robotics and AI， 2025， 12： No.1518965.
[9]	Ahmed T， Jannat S， Rahat A， et al. Knowledge distillation and weight pruning for two-step compression of ConvNets in rice leaf disease classification ［C］// NSysS 2024. New York： ACM， 2024： 72-78.
[10]	Heidorn C， Sabih M， Meyerhöfer N， et al. Hardware-aware evolutionary explainable filter pruning for convolutional neural networks ［J］. International Journal of Parallel Programming， 2024， 52（1/2）： 40-58.
[11]	Plochaet J， Goedemé T. Hardware-aware pruning for FPGA deep learning accelerators ［C］// CVPRW 2023. Piscataway： IEEE， 2023： 4482-4490.
[12]	Dantas P V， Sabino da Silva W， Cordeiro L C， et al. A comprehensive review of model compression techniques in machine learning ［J］. Applied Intelligence， 2024， 54（22）： 11804-11844.
[13]	Shi Y， Bai S， Wei X， et al. Lossy and lossless （L²） post-training model size compression ［C］// ICCV 2023. Piscataway： IEEE， 2023： 17500-17510.
[14]	王鹏，张嘉诚，范毓洋. 适应于硬件部署的神经网络剪枝量化算法［J］. 计算机工程与科学， 2024， 46（9）： 1547-1553.
	Wang Peng， Zhang Jiacheng， Fan Yuyang. A neural network pruning and quantization algorithm for hardware deployment ［J］. Computer Engineering and Science， 2024， 46（9）： 1547-1553.
[15]	Yang K， Jiang L， Deng J， et al. ASFRM： an array state self-feedback-based self-reconfiguration mechanism in a reconfigurable array processor ［J］. Journal of Circuits， Systems and Computers， 2025， 34（14）： No.2550305.
[16]	Hu Z， Shi Z， Karniadakis G E， et al. Hutchinson trace estimation for high-dimensional and high-order physics-informed neural networks ［J］. Computer Methods in Applied Mechanics and Engineering， 2024， 424： No.116883.
[17]	Yang L， Zheng C， Shen X， et al. OfpCNN： on-demand fine-grained partitioning for CNN inference acceleration in heterogeneous devices ［J］. IEEE Transactions on Parallel and Distributed Systems， 2023， 34（12）： 3090-3103.
[18]	Darbani P， Beitollahi H， Lotfi-Kamran P. Rei： a reconfigurable interconnection unit for array-based CNN accelerators ［J］. IEEE Transactions on Emerging Topics in Computing， 2023， 11（4）： 895-906.
[19]	Shinde T， Bhardwaj S. Mixed-precision is all you need for efficient document image classification ［C］// WACVW 2025. Piscataway： IEEE， 2025： 1195-1203.
[20]	Zhang D， Wang X， Wu Z， et al. A multi-scale automatic progressive pruning algorithm based on deep neural network ［C］// CCC 2024. Piscataway： IEEE， 2024： 8892-8897.
[21]	Bai S， Chen J， Shen X， et al. Unified data-free compression： pruning and quantization without fine-tuning ［C］// ICCV 2023. Piscataway： IEEE， 2023： 5853-5862.
[22]	Yang S， He S， Duan H， et al. APQ： automated DNN pruning and quantization for ReRAM-based accelerators ［J］. IEEE Transactions on Parallel and Distributed Systems， 2023， 34（9）： 2498-2511.
[23]	Han M， Wang L， Xiao L， et al. ReDas： a lightweight architecture for supporting fine-grained reshaping and multiple dataflows on systolic array ［J］. IEEE Transactions on Computers， 2024， 73（8）： 1997-2011.
[24]	Liu L， Jiang M， Sun J， et al. A CPU-FPGA based heterogeneous accelerator for DNA sequence alignment ［C］// ICICM 2024. Piscataway： IEEE， 2024： 655-660.
[25]	Sun W， Liu D， Zou Z， et al. Sense： model-hardware codesign for accelerating sparse CNNs on systolic arrays ［J］. IEEE Transactions on Very Large Scale Integration （VLSI） Systems， 2023， 31（4）： 470-483.
[26]	魏晓辉，关泽宇，王晨洋，等. 面向脉动阵列加速器的软硬件协同容错设计［J］. 计算机科学， 2025， 52（5）： 91-100.
	Wei Xiaohui， Guan Zeyu， Wang Chenyang， et al. Hardware-software co-design fault-tolerant strategies for systolic array accelerators［J］. Computer Science， 2025， 52（5）： 91-100.

项目	标签说明	版本型号描述
CPU	型号	Xeon Gold 6430
	物理核心数	16核
	内存频率	DDR5 4 800 MHz
GPU	型号	Nvidia RTX4090
	核心数	16384并行运算处理核心
	显存容量	24 GB
系统环境	Ubuntu22.04	—
深度学习框架	PyTorch1.8.1	—

项目	标签说明	版本型号描述
CPU	型号	Xeon Gold 6430
	物理核心数	16核
	内存频率	DDR5 4 800 MHz
GPU	型号	Nvidia RTX4090
	核心数	16384并行运算处理核心
	显存容量	24 GB
系统环境	Ubuntu22.04	—
深度学习框架	PyTorch1.8.1	—

模型	方法	Top-1准确率/%	剪枝率/%	FLOPs/10⁹
VGG16	基准方法	93.95	—	0.314
VGG16	本文方法	93.31	80	0.116
ResNet18	基准方法	93.47	—	0.558
ResNet18	本文方法	93.07	70	0.156

模型	方法	Top-1准确率/%	剪枝率/%	FLOPs/10⁹
VGG16	基准方法	93.95	—	0.314
VGG16	本文方法	93.31	80	0.116
ResNet18	基准方法	93.47	—	0.558
ResNet18	本文方法	93.07	70	0.156

网络	位宽	Top-1准确率/%
VGG16-Pruned	32.0	93.31
VGG16	5.9	92.62
ResNet18-Pruned	32.0	93.07
ResNet18	5.8	92.49

CNN pruning and quantization compression method for reconfigurable structures

面向可重构结构的CNN剪枝与量化压缩方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 16

References 26

Related Articles 15

Recommended Articles

Metrics

方法	类型	Top-1准确率/%		压缩后准确率损失百分点	压缩比
方法	类型	基准	压缩后	压缩后准确率损失百分点	压缩比
文献［19］方法	混合精度量化	86.09	85.30	0.79↓	6.50
文献［20］方法	结构化剪枝	93.59	93.45	0.14↓	8.90
文献［21］方法	结构化剪枝+混合精度量化	93.97	91.26	2.71↓	10.19
APQ^［22］	结构化剪枝+混合精度量化	81.61	81.20	0.41↓	13.90
本文方法	结构化剪枝+自适应混合精度量化	93.95	92.62	1.33↓	16.20

方法	推理时延/ms	加速比
未采用复用策略+统一16 bit精度	23.3	1.00
采用复用策略+统一16 bit精度	15.2	1.53
采用复用策略+混合精度量化	9.1	2.56

[1]	Huihui CHEN, Hongtao SUN, Boliang GUAN, Zhongqing HENG. Chinese character image retrieval algorithm in ancient books based on NetVLAD feature encoding [J]. Journal of Computer Applications, 2026, 46(3): 750-757.
[2]	Yanan LI, Mengyang GUO, Guojun DENG, Yunfeng CHEN, Jianji REN, Yongliang YUAN. Method for life prediction of parallel branching engine based on multi-modal fusion features [J]. Journal of Computer Applications, 2026, 46(1): 305-313.
[3]	Hongjun ZHANG, Gaojun PAN, Hao YE, Yubin LU, Yiheng MIAO. Multi-source heterogeneous data analysis method combining deep learning and tensor decomposition [J]. Journal of Computer Applications, 2025, 45(9): 2838-2847.
[4]	Chao SHI, Yuxin ZHOU, Qian FU, Wanyu TANG, Ling HE, Yuanyuan LI. Action recognition algorithm for ADHD patients using skeleton and 3D heatmap [J]. Journal of Computer Applications, 2025, 45(9): 3036-3044.
[5]	Peng PENG, Ziting CAI, Wenling LIU, Caihua CHEN, Wei ZENG, Baolai HUANG. Speech emotion recognition method based on hybrid Siamese network with CNN and bidirectional GRU [J]. Journal of Computer Applications, 2025, 45(8): 2515-2521.
[6]	Jinhao LIN, Chuan LUO, Tianrui LI, Hongmei CHEN. Thoracic disease classification method based on cross-scale attention network [J]. Journal of Computer Applications, 2025, 45(8): 2712-2719.
[7]	Yongpeng TAO, Shiqi BAI, Zhengwen ZHOU. Neural architecture search for multi-tissue segmentation using convolutional and transformer-based networks in glioma segmentation [J]. Journal of Computer Applications, 2025, 45(7): 2378-2386.
[8]	Yingjun ZHANG, Weiwei YAN, Binhong XIE, Rui ZHANG, Wangdong LU. Gradient-discriminative and feature norm-driven open-world object detection [J]. Journal of Computer Applications, 2025, 45(7): 2203-2210.
[9]	Dan WANG, Wenhao ZHANG, Lijuan PENG. Channel estimation of reconfigurable intelligent surface assisted communication system based on deep learning [J]. Journal of Computer Applications, 2025, 45(5): 1613-1618.
[10]	Baohua YUAN, Jialu CHEN, Huan WANG. Medical image segmentation network integrating multi-scale semantics and parallel double-branch [J]. Journal of Computer Applications, 2025, 45(3): 988-995.
[11]	Sheng YANG, Yan LI. Contrastive knowledge distillation method for object detection [J]. Journal of Computer Applications, 2025, 45(2): 354-361.
[12]	Dixin WANG, Jiahao WANG, Min LI, Hao CHEN, Guangyao HU, Yu GONG. Abnormal attack detection for underwater acoustic communication network [J]. Journal of Computer Applications, 2025, 45(2): 526-533.
[13]	Yonghong FAN, Heming HUANG. CnnPRL： progressive representation learning method for speech emotion recognition [J]. Journal of Computer Applications, 2025, 45(12): 3804-3812.
[14]	Jianhua REN, Jiahui CAO, Di JIA. Hand pose estimation based on mask prompts and attention [J]. Journal of Computer Applications, 2025, 45(12): 4012-4020.
[15]	Xinran XU, Shaobing ZHANG, Miao CHENG, Yang ZHANG, Shang ZENG. Bearings fault diagnosis method based on multi-pathed hierarchical mixture-of-experts model [J]. Journal of Computer Applications, 2025, 45(1): 59-68.