Survey of Neural Network Filter Pruning Technology

doi:10.3778/j.issn.1002-8331.2503-0280

Abstract

Abstract: With the improvement of software and hardware resources and computing capabilities, deep neural networks have rapidly developed in various fields such as computer vision, natural language processing, and image generation, leading to breakthroughs in areas such as autonomous driving and medical diagnosis through deep learning. However, as the depth of the model increases, the large number of parameters and the consumption of computing resources cause the model to become too complex to train and deploy in resource-constrained environments. To reduce the complexity of network models and improve their efficiency, researchers have proposed pruning methods to compress and accelerate models by reducing redundant parameters and connections. Filter pruning is one of the most important methods to optimize convolutional neural networks. It mainly changes the number of filter groups and feature channels to accelerate the network and does not depend on specific algorithm or hardware platform. So the paper reviews the research progress of filter pruning technology at home and abroad in recent years, classifies and summarizes the filter importance evaluation, pruning and fine-tuning mode design, and summarizes the experiments of the mainstream filter pruning methods to analyze the influence of filter pruning on model accuracy and parameter number, and also discusses the future research direction.

Key words: deep learning, deep convolutional neural network, model compression, filter pruning, acceleration of model optimization

摘要： 随着软硬件资源水平和计算能力的提高，深度神经网络在计算机视觉、自然语言处理、图像生成等多个领域迅速发展，引领深度学习在自动驾驶、医疗诊断等方向上不断突破。然而，随着模型深度的增加，庞大的参数量和计算资源消耗导致模型变得过于复杂，难以在资源受限的环境进行训练和部署。为了减少网络模型的复杂度，提高模型的效率，研究者们提出了剪枝方法，通过减少模型中的冗余参数和连接实现模型的压缩和加速。滤波器剪枝是优化卷积神经网络的重要方法之一，通过改变网络中滤波器组和特征通道的数目来加速网络，且不依赖于特定算法或硬件平台。梳理了近年来国内外滤波器剪枝技术的研究进展，从滤波器重要性评估、剪枝及微调方式设计两个方面进行分类总结，并对主流滤波器剪枝方法的实验进行归纳，分析滤波器剪枝对模型精度和参数量的影响，并对未来的研究方向加以探讨。

关键词: 深度学习, 深度卷积神经网络, 模型压缩, 滤波器剪枝, 模型优化加速

WANG Lin, SONG Quanrun, GENG Shichao, LUAN Zhongzhi. Survey of Neural Network Filter Pruning Technology[J]. Computer Engineering and Applications, 2026, 62(2): 1-25.

王琳, 宋权润, 耿世超, 栾钟治. 神经网络滤波器剪枝技术研究综述[J]. 计算机工程与应用, 2026, 62(2): 1-25.

References

[1] FUKUSHIMA K.Neocognitron：a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J].Biological Cybernetics，1980，36（4）：193-202.
[2] LECUN Y，BOTTOU L，BENGIO Y，et al.Gradient-based lea-rning applied to document recognition[J].Proceedings of the IEEE，1998，86（11）：2278-2324.
[3] KRIZHEVSKY A，SUTSKEVER I，HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM，2017，60（6）：84-90.
[4] SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].[2025-03-01].https：//arxiv.org/abs/1409.1556.
[5] HE K M，ZHANG X Y，REN S Q，et al.Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2016：770-778.
[6] ANWAR S，HWANG K，SUNG W.Structured pruning of deep convolutional neural networks[J].ACM Journal on Emerging Technologies in Computing Systems，2017，13（3）：1-18.
[7] DETTMERS T.8-bit approximations for parallelism in deep learning[EB/OL].[2025-03-01].https：//arxiv.org/abs/1511.04561.
[8] HOWARD A G，ZHU M L，CHEN B，et al.MobileNets：efficient convolutional neural networks for mobile vision applications[EB/OL].[2025-03-01].https：//arxiv.org/abs/1704.04861.
[9] HINTON G，VINYALS O，DEAN J.Distilling the knowledge in a neural network[EB/OL].[2025-03-01].https：//arxiv.org/abs/1503.02531.
[10] TAI C，XIAO T，ZHANG Y，et al.Convolutional neural networks with low-rank regularization[EB/OL].[2025-03-01].https：//arxiv.org/abs/1511.06067.
[11] HAN S，MAO H Z，DALLY W J.Deep compression：compressing deep neural networks with pruning，trained quantization and Huffman coding[EB/OL].[2025-03-01].https：//arxiv.org/abs/1510.00149.
[12] PARK J，NO A.Prune your model before distill it[C]//Proceedings of the European Conference on Computer Vision.Cham：Springer，2022：120-136.
[13] LECUN Y，DENKER J，SOLLA S.Optimal brain damage[C]//Advances in Neural Information Processing Systems，1989：598-605.
[14] HASSIBI B，STORK D G，WOLFF G J.Optimal brain surgeon and general network pruning[C]//Proceedings of the IEEE International Conference on Neural Networks.Piscataway：IEEE，2002：293-299.
[15] LIN M B，CAO L J，LI S J，et al.Filter sketch for network pruning[J].IEEE Transactions on Neural Networks and Lea-rning Systems，2022，33（12）：7091-7100.
[16] LIU Z，LI J G，SHEN Z Q，et al.Learning efficient convolutional networks through network slimming[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision.Piscataway：IEEE，2017：2755-2763.
[17] LI H，KADAV A，DURDANOVIC I，et al.Pruning filters for efficient ConvNets[EB/OL].[2025-03-01].https：//arxiv.org/abs/1608.08710.
[18] ELKERDAWY S，ELHOUSHI M，SINGH A，et al.To filter prune，or to layer prune，that is the question[C]//Proceedings of the Asian Conference on Computer Vision.Cham：Springer，2021：737-753.
[19] PONS I，YAMAMOTO B，REALI COSTA A H，et al.Effective layer pruning through similarity metric perspective[C]//Proceedings of the International Conference on Pattern Recognition.Cham：Springer，2025：423-438.
[20] HE Y，KANG G L，DONG X Y，et al.Soft filter pruning for accelerating deep convolutional neural networks[EB/OL].[2025-03-01].https：//arxiv.org/abs/1808.06866.
[21] LIN M B，JI R R，WANG Y，et al.HRank：filter pruning using high-rank feature map[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2020：1526-1535.
[22] LUO J H，WU J X，LIN W Y.ThiNet：a filter level pruning method for deep neural network compression[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision.Piscataway：IEEE，2017：5068-5076.
[23] LU J Q，WANG R Q，ZUO G P，et al.Enhancing CNN efficiency through mutual information-based filter pruning[J].Digital Signal Processing，2024，151：104547.
[24] HUANG Q G，ZHOU K，YOU S Y，et al.Learning to prune filters in convolutional neural networks[C]//Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision.Piscataway：IEEE，2018：709-718.
[25] LI Q H，LI C P，CHEN H.Filter pruning via probabilistic model-based optimization for accelerating deep convolutional neural networks[C]//Proceedings of the 14th ACM International Conference on Web Search and Data Mining.New York：ACM，2021：653-661.
[26] LIEBENWEIN L，BAYKAL C，LANG H，et al.Provable filter pruning for efficient neural networks[EB/OL].[2025-03-01].https：//arxiv.org/abs/1911.07412.
[27] 柳智.基于零模正则的神经网络剪枝方法[J].运筹与管理，2023，32（10）：102-107.
LIU Z.Pruning approach to neural networks based on zero-norm regularization[J].Operations Research and Management Science，2023，32（10）：102-107.
[28] GUYARD T，HERZET C，ELVIRA C，et al.A new branch-and-bound pruning framework for [L0]-regularized problems[EB/OL].[2025-03-01].https：//arxiv.org/abs/2406.03504.
[29] TMAMNA J，BEN AYED E，FOURATI R，et al.A CNN pru-ning approach using constrained binary particle swarm optimization with a reduced search space for image classification[J].Applied Soft Computing，2024，164：111978.
[30] JAYASIMHAN A P P.ResPrune：an energy-efficient restorative filter pruning method using stochastic optimization for accelerating CNN[J].Pattern Recognition，2024，155：110671.
[31] WANG W X，FU C，GUO J S，et al.COP：customized deep model compression via regularized correlation-based filter-level pruning[EB/OL].[2025-03-01].https：//arxiv.org/abs/1906. 10337.
[32] LIU G Z，ZHANG K，LV M B.SOKS：automatic searching of the optimal kernel shapes for stripe-wise network pruning[J].IEEE Transactions on Neural Networks and Learning Systems，2023，34（12）：9912-9924.
[33] ZHOU Y X，ZHAO H B，HEFENBROCK M，et al.Deep neural network pruning with progressive regularizer[C]//Proceedings of the 2024 International Joint Conference on Neural Networks.Piscataway：IEEE，2024：1-10.
[34] MOLCHANOV P，TYREE S，KARRAS T，et al.Pruning convolutional neural networks for resource efficient inference[C]//Proceedings of the 5th International Conference on Lea-rning Representations，2017.
[35] SHI J，XU J F，TASAKA K，et al.SASL：saliency-adaptive sparsity learning for neural network acceleration[J].IEEE Transactions on Circuits and Systems for Video Technology，2021，31（5）：2008-2019.
[36] MOLCHANOV P，MALLYA A，TYREE S，et al.Importance estimation for neural network pruning[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2020：11256-11264.
[37] YOU Z H，YAN K，YE J M，et al.Gate decorator：global filter pruning method for accelerating deep convolutional neural networks[EB/OL].[2025-03-01].https：//arxiv.org/abs/1909. 08174.
[38] SINGH D，RAO T P，VEERANJANEYULU N，et al.Design a multi-objective optimization with dynamic and global filter pruning strategy for convolutional neural network[J].Multimedia Tools and Applications，2025，84（3）：1345-1358.
[39] HE Y，LIU P，WANG Z W，et al.Filter pruning via geometric median for deep convolutional neural networks acceleration[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2020：4335-4344.
[40] HE Y，LIU P，ZHU L C，et al.Filter pruning by switching to neighboring CNNs with good attributes[J].IEEE Transactions on Neural Networks and Learning Systems，2023，34（10）：8044-8056.
[41] SONG K，YAO W S，ZHU X.Filter pruning viaSimilarity clustering forDeep convolutional neural networks[C]//Proceedings of the International Conference on Neural Information Processing.Cham：Springer，2023：88-99.
[42] MENG F X，CHENG H，LI K，et al.Filter grafting for deep neural networks[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2020：6598-6606.
[43] SHI C K，HAO Y X，LI G Y，et al.VNGEP：filter pruning based on von Neumann graph entropy[J].Neurocomputing，2023，528：113-124.
[44] 王彩玲，王炯，蒋国平.基于双DDPG的全局自适应滤波器剪枝方法[J].南京邮电大学学报（自然科学版），2021，41（5）：59-66.
WANG C L，WANG J，JIANG G P.Global adaptive filter pruning based on dual DDPG[J].Journal of Nanjing University of Posts and Telecommunications （Natural Science Edition），2021，41（5）：59-66.
[45] LILLICRAP T P，HUNT J J，PRITZEL A，et al.Continuous control with deep reinforcement learning[EB/OL].[2025-03-01].https：//arxiv.org/abs/1509.02971.
[46] TANG X L，YE S，SHI Y F，et al.Filter pruning based on information capacity and independence[J].IEEE Transactions on Neural Networks and Learning Systems，2025，36（5）：8401-8413.
[47] HUANG W L，WANG X J，ZHAO Z H，et al.Pruning CNN based on combinational filter deletion[C]//Proceedings of the 50th Annual Conference of the IEEE Industrial Electronics Society.Piscataway：IEEE，2025：1-6.
[48] YUAN T T，LI Z L，LIU B，et al.ARPruning：an automatic channel pruning based on attention map ranking[J].Neural Networks，2024，174：106220.
[49] MANA S C，RAJESH S，GOVERNOR K，et al.Revolutionizing neural network efficiency：introducing FPAC for filter pruning via attention consistency[J].Neural Computing and Applications，2024，36（2）：639-652.
[50] 王成龙，赵倩，赵琰，等.基于结构化剪枝的遥感飞机检测算法[J].电光与控制，2022，29（6）：37-41.
WANG C L，ZHAO Q，ZHAO Y，et al.Remote sensing aircraft detection algorithm based on structural pruning[J].Electronics Optics & Control，2022，29（6）：37-41.
[51] 冉梦影，杨文柱，尹群杰.无锚框目标检测模型通道剪枝方法[J].计算机科学与探索，2023，17（7）：1634-1643.
RAN M Y，YANG W Z，YIN Q J.Channel pruning method for anchor-free detector[J].Journal of Frontiers of Computer Science and Technology，2023，17（7）：1634-1643.
[52] LIAN S Y，ZHAO Y，PEI J H.DAAR：dual attention cooperative adaptive pruning rate by data-driven for filter pruning[J].Applied Intelligence，2025，55（6）：402.
[53] WANG Z，BOVIK A C，SHEIKH H R，et al.Image quality assessment：from error visibility to structural similarity[J].IEEE Transactions on Image Processing，2004，13（4）：600-612.
[54] CHEN Y M，WU G，SHUAI M R，et al.Fpar：filter pruning via attention and rank enhancement for deep convolutional neural networks acceleration[J].International Journal of Mac-hine Learning and Cybernetics，2024，15（7）：2973-2985.
[55] MA X，LI G L，LIU L，et al.Accelerating deep neural network filter pruning with mask-aware convolutional computations on modern CPUs[J].Neurocomputing，2022，505：375-387.
[56] LIN S H，HUANG W X，XIE J，et al.Filter pruning for efficient CNNs via knowledge-driven differential filter sampler[EB/OL].[2025-03-01].https：//arxiv.org/abs/2307.00198.
[57] CHEN X W，JI F R，CHU R X，et al.Data-free pruning of CNN using kernel similarity[J].Multimedia Systems，2025，31（3）：154.
[58] WANG X R，WANG J，TANG X，et al.Filter pruning via filters similarity in consecutive layers[C]//Proceedings of the 2023 IEEE International Conference on Acoustics，Speech and Signal Processing.Piscataway：IEEE，2023：1-5.
[59] LAI X C，WANG L K，ZHANG L Y.An iterative deep neural network pruning method based on filter redundancy assessment[C]//Proceedings of the 2024 5th International Seminar on Artificial Intelligence，Networking and Information Technology.Piscataway：IEEE，2024：289-294.
[60] YANG W，XIAO Y C.Structured pruning via feature channels similarity and mutual learning for convolutional neural network compression[J].Applied Intelligence，2022，52（12）：14560-14570.
[61] GUO Y，GAO W，LI G.Interpretable task-inspired adaptive filter pruning for neural networks under multiple constraints[J].International Journal of Computer Vision，2024，132（6）：2060-2076.
[62] SHAO M W，DAI J H，KUANG J D，et al.A dynamic CNN pruning method based on matrix similarity[J].Signal，Image and Video Processing，2021，15（2）：381-389.
[63] XUE Y F，YAO W S，PENG S Y，et al.Automatic filter pruning algorithm for image classification[J].Applied Intelligence，2024，54（1）：216-230.
[64] LIN H，PENG Y F，ZHANG Y B，et al.Filter pruning by high-order spectral clustering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2025，47（4）：2402-2415.
[65] ERICK F X，SAWANT S S，G?B S，et al.A simple and effective convolutional filter pruning based on filter dissimilarity analysis[C]//Proceedings of the 14th International Conference on Agents and Artificial Intelligence，2022：139-145.
[66] GENG L L，NIU B N.APSSF：adaptive CNN pruning based on structural similarity of filters[J].International Journal of Computational Intelligence Systems，2024，17（1）：129.
[67] PHAM V T，ZNIYED Y，NGUYEN T P.Hybrid network compression through tensor decompositions and pruning[C]//Proceedings of the 2024 32nd European Signal Processing Conference.Piscataway：IEEE，2024：1052-1056.
[68] LIU Z H，XU J Z，PENG X L，et al.Frequency-domain dyn-amic pruning for convolutional neural networks[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems.New York：ACM，2018：1051-1061.
[69] HE Y，LIU P，ZHU L，et al.Meta filter pruning to accelerate deep convolutional neural networks[EB/OL].[2025-03-01].https：//arxiv.org/abs/1904.03961.
[70] LIN M B，CAO L J，ZHANG Y X，et al.Pruning networks with cross-layer ranking & k-reciprocal nearest filters[J].IEEE Transactions on Neural Networks and Learning Systems，2023，34（11）：9139-9148.
[71] PARK M，KIM D，PARK C，et al.REPrune：channel pruning via kernel representative selection[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2024：14545-14553.
[72] SAWANT S S，BAUER J，ERICK F X，et al.An optimal-score-based filter pruning for deep convolutional neural networks[J].Applied Intelligence，2022，52（15）：17557-17579.
[73] SARVANI C H，GHORAI M，SHABBEER BASHA S H.PRF：deep neural network compression by systematic pruning of redundant filters[J].Neural Computing and Applications，2024，36（33）：20607-20616.
[74] QU H C，ZHANG X C.Pruning networks using filters similarity stability[C]//Proceedings of the 2023 6th International Conference on Software Engineering and Information Management.New York：ACM，2023：256-260.
[75] KHAN N A，SAADMAN RAFAT A M.Pruning convolution neural networks using filter clustering based on normalized cross-correlation similarity[J].Journal of Information and Telecommunication，2025，9（2）：190-208.
[76] ZHUO H Y，QIAN X L，FU Y W，et al.SCSP：spectral clustering filter pruning with soft self-adaption manners[EB/OL].[2025-03-01].https：//arxiv.org/abs/1806.05320.
[77] WU Z H，LI F X，ZHU Y，et al.A filter pruning method of CNN models based on feature maps clustering[J].Applied Sciences，2022，12（9）：4541.
[78] LIU Y J，FAN K F，WU D K，et al.Structural similarity filter pruning of frequency domain edge for convolutional neural networks[C]//Proceedings of the 2024 4th International Conference on Consumer Electronics and Computer Engineering.Piscataway：IEEE，2024：148-152.
[79] GENG X，GAO J X，ZHANG Y H，et al.Complex hybrid weighted pruning method for accelerating convolutional neural networks[J].Scientific Reports，2024，14：5570.
[80] CHEN S W，SUN W Z，HUANG L.WHC：weighted hybrid criterion for filter pruning on convolutional neural networks[C]//Proceedings of the 2023 IEEE International Conference on Acoustics，Speech and Signal Processing.Piscataway：IEEE，2023：1-5.
[81] GHIMIRE D，KIM S H.Magnitude and similarity based variable rate filter pruning for efficient convolution neural networks[J].Applied Sciences，2023，13（1）：316.
[82] GENG L L，NIU B N.Pruning convolutional neural networks via filter similarity analysis[J].Machine Learning，2022，111（9）：3161-3180.
[83] BAI Z W，SONG S F.Physics-based pruning neural network for global sensitivity analysis[J].Reliability Engineering & System Safety，2025，258：110925.
[84] CHEN F Y，HSU Y J，LU C H，et al.Compressing deep neural networks with goal-specific pruning and self-distillation[J].ACM Transactions on Knowledge Discovery from Data，2025，19（4）：1-27.
[85] SAKAI Y，ETO Y，TERANISHI Y.Structured pruning for deep neural networks with adaptive pruning rate derivation based on connection sensitivity and loss function[J].Journal of Advances in Information Technology，2022，13（3）：295-300.
[86] HEIDORN C，SABIH M，MEYERH?FER N，et al.Hardware-aware evolutionary explainable filter pruning for convolutional neural networks[J].International Journal of Parallel Programming，2024，52（1）：40-58.
[87] BABAIEE Z，LIEBENWEIN L，HASANI R，et al.End-to-end sensitivity-based filter pruning[EB/OL].[2025-03-01].https：// arxiv.org/abs/2204.07412.
[88] YANG C B，LIU H Y.Channel pruning based on convolutional neural network sensitivity[J].Neurocomputing，2022，507：97-106.
[89] SINGH P，KADI V S R，VERMA N，et al.Stability based filter pruning for accelerating deep CNNs[C]//Proceedings of the 2019 IEEE Winter Conference on Applications of Computer Vision.Piscataway：IEEE，2019：1166-1174.
[90] KUANG J D，SHAO M W，WANG R，et al.Network pruning via probing the importance of filters[J].International Journal of Machine Learning and Cybernetics，2022，13（9）：2403-2414.
[91] MOUSA-PASANDI M，HAJABDOLLAHI M，KARIMI N，et al.Convolutional neural network pruning using filter att-enuation[C]//Proceedings of the 2020 IEEE International Conference on Image Processing.Piscataway：IEEE，2020：2905-2909.
[92] TAN C M J，MOTANI M.DropNet：reducing neural network complexity via iterative pruning[C]//Proceedings of the International Conference on Machine Learning，2020.
[93] 褚晶辉，李梦，吕卫.基于深度学习的自适应动态滤波器剪枝方法[J].激光与光电子学进展，2022，59（24）：2415003.
CHU J H，LI M，LYU W.Adaptive dynamic filter pruning approach based on deep learning[J].Laser & Optoelectronics Progress，2022，59（24）：2415003.
[94] ELKERDAWY S，ELHOUSHI M，ZHANG H，et al.Fire together wire together：a dynamic pruning approach with self-supervised mask prediction[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2022：12444-12453.
[95] HE Z Q，QIAN Y G，WANG Y Q，et al.Filter pruning via Feature discrimination inDeep neural networks[C]//Proceedings of the European Conference on Computer Vision.Cham：Spr-inger，2022：245-261.
[96] CATANZARO B，CHOCHOWSKI M，JOSHI R，et al.Compact language models via pruning and knowledge distillation[C]//Advances in Neural Information Processing System，2024：41076-41102.
[97] ZHANG C.Intelligent fault prediction and diagnosis of intelligent networked vehicle based on filter pruning with snapshot stacked ensemble deep neural network[C]//Proceedings of the 2024 4th International Conference on Mobile Networks and Wireless Communications.Piscataway：IEEE，2025：1-5.
[98] 白学营，陈维常，徐菲，等.应用感知的深度神经网络剪枝方法[J].宇航总体技术，2024，8（5）：64-73.
BAI X Y，CHEN W C，XU F，et al.A pruning method for deep neural networks using perception[J].Astronautical Systems Engineering Technology，2024，8（5）：64-73.
[99] LI Z M，ZUO X J，SONG Y P，et al.A multi-agent reinforcement learning based approach for automatic filter pruning[J].Scientific Reports，2024，14：31193.
[100] TANG C，ABBATEMATTEO B，HU J H，et al.Deep reinforcement learning for robotics：a survey of real-world successes[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2025：28694-28698.
[101] GANJDANESH A，GAO S Q，HUANG H.Jointly training and pruning CNNs via learnable agent guidance and alignment[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2024：16058-16069.
[102] YU F，HAN C Q，WANG P C，et al.HFP：hardware-aware filter pruning for deep convolutional neural networks acceleration[C]//Proceedings of the 2020 25th International Conference on Pattern Recognition.Piscataway：IEEE，2021：255-262.
[103] LIN J，RAO Y，LU J，et al.Runtime neural pruning[C]//Adv-ances in Neural Information Processing Systems，2017：2181-2191.
[104] 刘阳，滕颖蕾，牛涛，等.基于深度强化学习的滤波器剪枝方案[J].北京邮电大学学报，2023，46（3）：31-36.
LIU Y，TENG Y L，NIU T，et al.Filter pruning algorithm based on deep reinforcement learning[J].Journal of Beijing University of Posts and Telecommunications，2023，46（3）：31-36.
[105] XIONG J C，WANG Q，YANG Z R，et al.Parametrized deep Q-networks learning：reinforcement learning with discrete-continuous hybrid action space[EB/OL].[2025-03-01].https：//arxiv.org/abs/1810.06394.
[106] ZHOU Y F，ZHANG Y，WANG Y F，et al.Accelerate CNN via recursive Bayesian pruning[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision.Piscataway：IEEE，2020：3305-3314.
[107] DING X H，HAO T X，TAN J C，et al.ResRep：lossless CNN pruning via decoupling remembering and forgetting[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision.Piscataway：IEEE，2022：4490-4500.
[108] LIN M B，JI R R，LI S J，et al.Network pruning using adaptive exemplar filters[J].IEEE Transactions on Neural Networks and Learning Systems，2022，33（12）：7357-7366.
[109] ZHENG Y B，SUN P，REN Q，et al.A novel and efficient model pruning method for deep convolutional neural networks by evaluating the direct and indirect effects of filters[J].Neurocomputing，2024，569：127124.
[110] JIANG X R，WANG N N，XIN J W，et al.Learning lightweight super-resolution networks with weight pruning[J].Neural Networks，2021，144：21-32.
[111] YU X，SERRA T，RAMALINGAM S，et al.The combinatorial brain surgeon：pruning weights that cancel one another in neural networks[EB/OL].[2025-03-01].https：//arxiv.org/abs/2203.04466.
[112] 孙环龙，王汝凉，李双，等.前馈神经网络结构新型剪枝算法研究[J].广西师范学院学报（自然科学版），2013，30（4）：55-60.
SUN H L，WANG R L，LI S，et al.A new pruning algorithm for feedforward neural network[J].Journal of Guangxi Teachers Education University （Natural Science Edition），2013，30（4）：55-60.
[113] WEN W，WU C P，WANG Y D，et al.Learning structured sparsity in deep neural networks[C]//Advances in Neural Information Processing Systems，2016：2074-2082.
[114] SCARDAPANE S，COMMINIELLO D，HUSSAIN A，et al.Group sparse regularization for deep neural networks[J].Neurocomputing，2017，241：81-89.
[115] LIU L Y，ZHANG S L，KUANG Z H，et al.Group fisher pruning for practical network compression[C]//Proceedings of the International Conference on Machine Learning，2021：7021-7032.
[116] WEI H，WANG Z L，HUA G X，et al.Automatic group-based structured pruning for deep convolutional networks[J].IEEE Access，2022，10：128824-128834.
[117] FANG G F，MA X Y，MI M B，et al.Isomorphic pruning forVision models[C]//Proceedings of the European Conference on Computer Vision.Cham：Springer，2025：232-250.
[118] 赵汉理，史开杰，金小刚，等.基于概率的深度可分离卷积网络通道剪枝[J].计算机科学技术学报，2022，37（3）：584-600.
ZHAO H L，SHI K J，JIN X G，et al.Probability-based channel pruning for depthwise separable convolutional networks[J].Journal of Computer Science and Technology，2022，37（3）：584-600.
[119] HE Y H，ZHANG X Y，SUN J.Channel pruning for accelerating very deep neural networks[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision.Piscataway：IEEE，2017：1398-1406.
[120] 刘相呈，曹健，姚宏毅，等.基于自适应剪枝率与高效权重继承的神经网络通道剪枝方法[J].北京大学学报（自然科学版），2023，59（5）：764-772.
LIU X C，CAO J，YAO H Y，et al.AdaPruner：adaptive channel pruning and effective weights inheritance[J].Acta Scientiarum Naturalium Universitatis Pekinensis，2023，59（5）：764-772.
[121] XIE Z Y，FU Y，TIAN S Z，et al.Pruning with compensation：efficient channel pruning for deep convolutional neural networks[EB/OL].[2025-03-01].https：//arxiv.org/abs/2108. 13728.
[122] SUN X L，SHI H.Towards better structured pruning saliency by reorganizing convolution[C]//Proceedings of the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision.Piscataway：IEEE，2024：2193-2203.
[123] DONG Z，DUAN Y Z，ZHOU Y，et al.Weight-adaptive channel pruning for CNNs based on closeness-centrality modeling[J].Applied Intelligence，2024，54（1）：201-215.
[124] MENG F，CHENG H，LI K，et al.Pruning filter in filter[C]//Advances in Neural Information Processing Systems，2020：17629-17640.
[125] LIU J J，HUANG L J，FENG M L，et al.SSFP：a structured stripe-filter pruning method for deep neural networks[C]//Proceedings of the 2024 13th International Conference on Communications，Circuits and Systems.Piscataway：IEEE，2024：80-84.
[126] 张敏灵，胡清华，李宇峰.机器学习及其应用-2021[M].北京：清华大学出版社，2021：34-49.
ZHANG M L，HU Q H，LI Y F.Machine learning and its application-2021[M].Beijing：Tsinghua University Press，2021：34-49.
[127] 胡骏，黄启鹏，刘嘉昕，等.引入概率分布的深度神经网络贪婪剪枝[J].中国图象图形学报，2021，26（1）：198-207.
HU J，HUANG Q P，LIU J X，et al.Greedy pruning of deep neural networks fused with probability distribution[J].Journal of Image and Graphics，2021，26（1）：198-207.
[128] 王勇，戚浩金，刘宇，等.贪心剪枝：无需搜索的自动剪枝算法[J].软件工程与应用，2021，10（4）：595-605.
WANG Y，QI H J，LIU Y，et al.Greedy pruning：an automatic pruning algorithm without search[J].Software Engineering and Applications，2021，10（4）：595-605.
[129] PUROHIT K，PARVATHGARI A R，BHATTACHARYA S.A greedy hierarchical approach to whole-network filter-pruning in CNNs[EB/OL].[2025-03-01].https：//arxiv.org/abs/2409.03777.
[130] SHI D C，TAO C F，JIN Y，et al.UPop：unified and progressive pruning for compressing vision-language transformers[EB/OL].[2025-03-01].https：//arxiv.org/abs/2301.13741.
[131] MISRA D，RUNWAL B，CHEN T L，et al.APP：anytime progressive pruning[EB/OL].[2025-03-01].https：//arxiv.org/abs/2204.01640.
[132] HE Y，DONG X Y，KANG G L，et al.Asymptotic soft filter pruning for deep convolutional neural networks[J].IEEE Transactions on Cybernetics，2020，50（8）：3594-3604.
[133] HU C，ZHANG S Q，TAO K W，et al.SFPBL：soft filter pruning based on logistic growth differential equation for neural network[J].Computers，Materials and Continua，2025，82（3）：4913-4930.
[134] YANG L，GU S Q，SHEN C Y，et al.Soft independence guided filter pruning[J].Pattern Recognition，2024，153：110488.
[135] 周成，李军华，黎明，等.卷积效力评价机制驱动的深度神经网络全局剪枝[J].中国科学：信息科学，2023，53（5）：878-898.
ZHOU C，LI J H，LI M，et al.Global pruning of deep neural networks driven by convolutional effectiveness evaluation mechanism[J].Scientia Sinica （Informationis），2023，53（5）：878-898.
[136] 孙文宇，曹健，李普，等.基于全局信息的卷积神经网络模型剪枝微调优化方法[J].北京大学学报（自然科学版），2021，57（4）：790-794.
SUN W Y，CAO J，LI P，et al.Pruning and fine-tuning optimization method of convolutional neural network based on global information[J].Acta Scientiarum Naturalium Universitatis Pekinensis，2021，57（4）：790-794.
[137] 李倩，王永县，朱友芹.人工神经网络混合剪枝算法[J].清华大学学报（自然科学版），2005，45（6）：831-834.
LI Q，WANG Y X，ZHU Y Q.Hybrid pruning algorithm for artificial neural network training[J].Journal of Tsinghua University （Science and Technology），2005，45（6）：831-834.
[138] WANG X D，ZHENG Z D，HE Y，et al.Progressive local filter pruning for image retrieval acceleration[J].IEEE Transactions on Multimedia，2023，25：9597-9607.
[139] MISHRA A K，CHAKRABORTY M.Does local pruning offer task-specific models to learn effectively? [C]//Proceedings of the Student Research Workshop Associated with RANLP 2021，2021：118-125.
[140] TANAKA H，KUNIN D，YAMINS D L K，et al.Pruning neural networks without any data by iteratively conserving synaptic flow[EB/OL].[2025-03-01].https：//arxiv.org/abs/2006.05467.
[141] LEE N，AJANTHAN T，TORR P H S.SNIP：single-shot network pruning based on connection sensitivity[EB/OL].[2025-03-01].https：//arxiv.org/abs/1810.02340.
[142] HUANG Z H，WANG N Y.Data-driven sparse structure selection for deep neural networks[C]//Proceedings of the European Conference on Computer Vision.Cham：Springer，2018：317-334.
[143] EVCI U，GALE T，MENICK J，et al.Rigging the lottery：making all tickets winners[EB/OL].[2025-03-01].https：//arxiv.org/abs/1911.11134.
[144] LIU Z，SUN M J，ZHOU T H，et al.Rethinking the value of network pruning[EB/OL].[2025-03-01].https：//arxiv.org/abs/1810.05270.
[145] RENDA A，FRANKLE J，CARBIN M.Comparing rewinding and fine-tuning in neural network pruning[EB/OL].[2025-03-01].https：//arxiv.org/abs/2003.02389.
[146] DONG X Y，HUANG J S，YANG Y，et al.More is less：a more complicated network with less inference complexity[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2017：1895-1903.
[147] GAO S Q，ZHANG Y F，HUANG F H，et al.BilevelPruning：unified dynamic and static channel pruning for convolutional neural networks[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2024：16090-16100.
[148] TANG Y H，WANG Y H，XU Y X，et al.Manifold regularized dynamic network pruning[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2021：5016-5026.
[149] GAO X T，ZHAO Y R，DUDZIAK ?，et al.Dynamic channel pruning：feature boosting and suppression[EB/OL].[2025-03-01].https：//arxiv.org/abs/1810.05331.
[150] ZHANG T Y，YE S K，ZHANG K Q，et al.A systematic DNN weight pruning framework using alternating direction method of multipliers[C]//Proceedings of the European Conference on Computer Vision.Cham：Springer，2018：191-207.
[151] HE Y，DING Y H，LIU P，et al.Learning filter pruning criteria for deep convolutional neural networks acceleration[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2020：2006-2015.
[152] ABBASI-ASL R，YU B.Structural compression of convolutional neural networks[EB/OL].[2025-03-01].https：//arxiv.org/abs/1705.07356.
[153] KHAKZAR A.Rethinking feature attribution for neural network explanation[D].München：Technische Universit?t München，2023.
[154] LUO J H，WU J X.An entropy-based pruning method for CNN compression[EB/OL].[2025-03-01].https：//arxiv.org/abs/1706.05791.
[155] INTRARAPRASIT M，CHITSOBHUK O.Filter pruning with convolutional approximation small model framework[J].Computation，2023，11（9）：176.
[156] KO H，KANG J K，KIM Y.An efficient and fast filter pruning method for object detection in embedded systems[C]//Proceedings of the 2024 IEEE 6th International Conference on AI Circuits and Systems.Piscataway：IEEE，2024：204-207.
[157] ZHOU L Y，LIU X Y.MDPruner：meta-learning driven dyn-amic filter pruning for efficient object detection[J].IEEE Access，2024，12：136925-136935.
[158] YU G Y，CAI R L，LUO Y T，et al.A-pruning：a lightweight pineapple flower counting network based on filter pruning[J].Complex & Intelligent Systems，2024，10（2）：2047-2066.
[159] WANG M，WANG Z R，LI B，et al.Filter collaborative contribution pruning method based on the importance of different-scale layers for surface defect detection[J].Measurement，2024，231：114507.
[160] GKRISPANIS K，GKALELIS N，MEZARIS V.Filter-pruning of lightweight face detectors using a geometric Median criterion[C]//Proceedings of the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops.Piscataway：IEEE，2024：280-289.
[161] TANG Q，ZHANG B W，LIU J J，et al.Dynamic token pruning in plain vision transformers for semantic segmentation[C]//Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision.Piscataway：IEEE，2024：777-786.
[162] TOUHEED M，ZUBAIR U，SABIR D，et al.Applications of pruning methods in natural language processing[J].IEEE Access，2024，12：89418-89438.
[163] LING G，LIU Q W，WANG Z Y，et al.SlimGPT：layer-wise structured pruning for large language models[C]//Advances in Neural Information Processing Systems，2024：107112-107137.
[164] SHIM K，YUN J，CHOI S.SNP：structured neuron-level pruning toPreserve attention scores[C]//Proceedings of the European Conference on Computer Vision.Cham：Springer，2025：90-104.
[165] CHU X W，DONG P J，GUO Y K，et al.Discovering sparsity allocation for layer-wise pruning of large language models[C]//Advances in Neural Information Processing Systems，2024：141292-141317.
[166] ILHAN F，SU G，TEKIN S F，et al.Resource-efficient transformer pruning for finetuning of large models[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2024：16206-16215.
[167] GAO S Q，LI J Y，ZHANG Z Y，et al.Device-wise federated network pruning[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2024：12342-12352.
[168] HUANG H，ZHUANG W M，CHEN C，et al.FedMef：towards memory-efficient federated dynamic pruning[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2024：27538-27547.
[169] SHI C Y，ZHOU W Y，WU X Y，et al.Lightweight automatic modulation classification method using filter pruning via geometric Median[C]//Proceedings of the 2024 6th Int-ernational Conference on Robotics，Intelligent Control and Artificial Intelligence.Piscataway：IEEE，2024：200-204.
[170] LI S Q，CHEN J，XIANG J Y，et al.AutoDFP：automatic data-free pruning via channel similarity reconstruction[EB/OL].[2025-03-01].https：//arxiv.org/abs/2403.08204.
[171] JIANG M N，WANG J C，ELDEBIKY A，et al.Class-aware pruning for efficient neural networks[C]//Proceedings of the 2024 Design，Automation & Test in Europe Conference & Exhibition.Piscataway：IEEE，2024：1-6.
[172] LI G Q，LI R G，LI T，et al.SFP：similarity-based filter pru-ning for deep neural networks[J].Information Sciences，2025，689：121418.
[173] 闫雅茹.平衡幅度和相似度的滤波器剪枝算法[J].建模与仿真，2025，14（1）：353-365.
YAN Y R.Filter pruning algorithm for balancing amplitude and similarity[J].Modeling and Simulation，2025，14（1）：353-365.
[174] PHAM V T，ZNIYED Y，NGUYEN T P.Efficient tensor decomposition-based filter pruning[J].Neural Networks，2024，178：106393.
[175] PHAM V T，ZNIYED Y，NGUYEN T P.Enhanced network compression through tensor decompositions and pruning[J].IEEE Transactions on Neural Networks and Learning Systems，2025，36（3）：4358-4370.
[176] LIU Y J，FAN K F，ZHOU W J.Iterative filter pruning with combined feature maps and knowledge distillation[J].International Journal of Machine Learning and Cybernetics，2025，16（3）：1955-1969.
[177] KIM J，EL HALABI M，JI M，et al.LayerMerge：neural network depth compression through layer pruning and mer-ging[EB/OL].[2025-03-01].https：//arxiv.org/abs/2406.12837.
[178] 薛紫涵，葛海波，王淑贤，等.融合快速边缘注意力的Transformer跟踪算法[J].计算机工程与应用，2025，61（1）：221-231.
XUE Z H，GE H B，WANG S X，et al.Transformer tracking algorithm integrating fast edge attention[J].Computer Eng-ineering and Applications，2025,61（1）：221-231.
[179] WU X D，GAO S Q，ZHANG Z Y，et al.Auto-train-once：controller network guided automatic network pruning from scratch[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2024：16163-16173.
[180] XU X Z，CHEN J，LI Z S，et al.Towards efficient filter pruning via adaptive automatic structure search[J].Engineering Applications of Artificial Intelligence，2024，133：108398.
[181] CHEN Z L，LIU C B，YANG W D，et al.LAP：latency-aware automated pruning with dynamic-based filter selection[J].Neural Networks，2022，152：407-418.