计算机科学 ›› 2026, Vol. 53 ›› Issue (4): 277-283.doi: 10.11896/jsjkx.250600108
郑毅, 贾星昊, 张骏温, 任爽
ZHENG Yi, JIA Xinghao, ZHANG Junwen, REN Shuang
摘要： 经典神经网络的规模、计算时长很难进一步突破,难以兼顾轻量化和高性能,在目前大数据时代下成为了解决海量数据的图像分类问题的瓶颈。而混合量子经典神经网络具有量子计算与经典计算的优势,能够进行高效的并行计算并具有较好的普适性。为此,设计了混合量子经典长-短距离特征扩展网络(Hybrid Quantum-Classical Long-Short Range Feature Extension Neural Network,HQC-LSNet),它是一种包含多个混合模块的多分支结构。通过多种量子旋转门及受控-Z门构成量子解耦全连接注意力机制,利用量子特性从量子增强特征空间中高效地获取长距离特征;与此同时,采用经典卷积模块获取短距离特征,并以组合特征图的方式进行特征扩展。在MNIST的十分类以及CIFAR-10数据集上的三分类这两个图像多分类任务上测试其准确率分别为99.42%和91.42%,相较于对应的经典模型及混合量子经典模型均有提升,而且该模型的参数量与时间复杂度相较于经典模型均有所减小。
中图分类号:
| [1]CHEN F,LI S,HAN J,et al.Review of lightweight deep convolutional neural networks[J].Archives of Computational Me-thods in Engineering,2024,31(4):1915-1937. [2]XU X,DING Y,HU S X,et al.Scaling for edge inference ofdeep neural networks[J].Nature Electronics,2018,1(4):216-222. [3]HOWARD A G,ZHU M,CHEN B,et al.Mobilenets:Efficient convolutional neural networks for mobile vision applications[J].arXiv:1704.04861,2017. [4]HOWARD A,SANDLER M,CHU G,et al.Searching for mobilenetv3[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:1314-1324. [5]HAN K,WANG Y,TIAN Q,et al.Ghostnet:More featuresfrom cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:1580-1589. [6]TANG Y,HAN K,GUO J,et al.GhostNetv2:Enhance cheapoperation with long-range attention[J].Advances in Neural Information Processing Systems,2022,35:9969-9982. [7]SU T,LIU A,SHI Y,et al.IremulbNet:Rethinking the inverted residual architecture for image recognition[J].Neural Networks,2024,172:106140. [8]ZHANG H,MA Y,ZHANG K,et al.FMGNet:An efficient feature-multiplex group network for real-time vision task[J].Pattern Recognition,2024,156:110698. [9]SCHULD M,FINGERHUTH M,PETRUCCIONE F.Imple-menting a distance-based classifier with a quantum interference circuit[J].Europhysics Letters,2017,119(6):60002. [10]WANG J,ZHANG R,JIANG N.Survey on Quantum Machine Learning[J].Journal of Software,2024,35(8):3843-3877. [11]LLOYD S,MOHSENI M,REBENTROST P.Quantum algo-rithms for supervised and unsupervised machine learning[J].arXiv:1307.0411,2013. [12]FEDOROV D A,PENG B,GOVIND N,et al.VQE method:a short survey and recent developments[J].Materials Theory,2022,6(1):2. [13]HUR T,KIM L,PARK D K.Quantum convolutional neuralnetwork for classical data classification[J].Quantum Machine Intelligence,2022,4(1):3. [14]HENDERSON M,SHAKYA S,PRADHAN S,et al.Quanvolutional neural networks:powering image recognition with quantum circuits[J].Quantum Machine Intelligence,2020,2(1):2. [15]GUPTA S,KONAR D,AGGARWAL V.A Scalable Quantum Non-local Neural Network for Image Classification[J].arXiv:2407.18906,2024. [16]SENOKOSOV A,SEDYKH A,SAGINGALIEVA A,et al.Quantum machine learning for image classification[J].Machine Learning:Science and Technology,2024,5(1):015040. [17]RAO G V E,RAJITHA B,SRINIVASU P N,et al.Hybrid framework for respiratory lung diseases detection based on classical CNN and quantum classifiers from chest X-rays[J].Biomedical Signal Processing and Control,2024,88:105567. [18]XIONG Q B,MIAO Q G,YANG T.Malicious Code Detection Method Based on Hybrid Quantum Convolutional Neural Network[J].Computer Science,2025,52(3):385-390. [19]FAN F,SHI Y,GUGGEMOS T,et al.Hybrid quantum-classical convolutional neural network model for image classification[J].IEEE Transactions on Neural Networks and Learning Systems,2024,35(12):18145-18159. [20]LIU J,LIM K H,WOOD K L,et al.Hybrid quantum-classical convolutional neural networks[J].Science China Physics,Mechanics & Astronomy,2021,64(9):290311. [21]FENG Y,LI Y,LI J,et al.Variational Shadow Quantum Cir-cuits Assisted Quantum Convolutional Neural Network[J].Advanced Quantum Technologies,2025,8(8):2400510. [22]WEI S J,CHEN Y H,ZHOU Z R,et al.A quantum convolutional neural network on NISQ devices[J].AAPPS Bulletin,2022,32:1-11. [23]LIU Z,LIN Y,CAO Y,et al.Swin transformer:Hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:10012-10022. [24]MEHTA S,RASTEGARI M.Mobilevit:light-weight,general-purpose,and mobile-friendly vision transformer[J].arXiv:2110.02178,2021. [25]SHI J,ZHAO R X,WANG W,et al.QSAN:A near-term achievable quantum self-attention network[J].IEEE Transactions on Neural Networks and Learning Systems,2025,38(8):13995-14008. [26]ZHAO R X,SHI J,LI X.QKSAN:A Quantum Kernel Self-Attention Network[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2024,46(12):10184-10195. [27]JADERBERG M,VEDALDI A,ZISSERMAN A.Speeding up convolutional neural networks with low rank expansions[J].arXiv:1405.3866,2014. [28]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010. [29]LIU J,LIM K H,WOOD K L,et al.Hybrid quantum-classical convolutional neural networks[J].Science China Physics,Mechanics & Astronomy,2021,64(9):290311. [30]GRANT E,BENEDETTI M,CAO S,et al.Hierarchical quantum classifiers[J].NPJ Quantum Information,2018,4(1):65. [31]KANDALA A,MEZZACAPO A,TEMME K,et al.Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets[J].Nature,2017,549(7671):242-246. |
| [1] | 李奕丹, 崔建英, 熊明辉. 自然语言语义表示的范畴论建模:系统综述与组合机制分析 Category-Theoretic Semantic Representation: Systematic Review and Compositional Mechanism Analysis 计算机科学, 2026, 53(4): 337-346. https://doi.org/10.11896/jsjkx.251000136 |
| [2] | 李晖, 刘述娟, 鞠明媚, 王杰鹏, 姬迎松. NISQ量子线路高频-密集量子门集策略优化算法 High Frequency-Dense Quantum Gate Set Optimization Algorithm for Quantum Circuit in NISQ Era 计算机科学, 2026, 53(4): 112-120. https://doi.org/10.11896/jsjkx.241200213 |
| [3] | 陈涵, 徐泽锋, 蒋究, 樊凡, 章军建, 何楚, 王文伟. 基于大语言模型和深度网络的认知评估量表自动诊断 Large Language Model and Deep Network Based Cognitive Assessment Automatic Diagnosis 计算机科学, 2026, 53(3): 41-51. https://doi.org/10.11896/jsjkx.250600034 |
| [4] | 张兴兰, 容潇军. 基于变分量子的离散对数求解算法 Variational Quantum Algorithm for Solving Discrete Logarithms 计算机科学, 2026, 53(1): 353-362. https://doi.org/10.11896/jsjkx.241100181 |
| [5] | 雷帅, 仇明鑫, 柳先辉, 张颖瑶. 基于多尺度深度可分离ResNet的废弃家电回收图像分类模型 Image Classification Model for Waste Household Appliance Recycling Based on Multi-scaleDepthwise Separable ResNet 计算机科学, 2025, 52(6A): 240500057-7. https://doi.org/10.11896/jsjkx.240500057 |
| [6] | 王春东, 张清华, 付浩然. 一种结合数据集蒸馏的联邦学习隐私保护方法 Federated Learning Privacy Protection Method Combining Dataset Distillation 计算机科学, 2025, 52(6A): 240500132-7. https://doi.org/10.11896/jsjkx.240500132 |
| [7] | 张静, 王宇平. 基于半直积的双平台密钥协商协议 Dual-platform Key Agreement Protocol Based on Semidirect Product 计算机科学, 2025, 52(6A): 240600036-6. https://doi.org/10.11896/jsjkx.240600036 |
| [8] | 张曜麟, 刘晓楠, 杜帅岐, 廉德萌. 基于矩阵乘积算符的混合量子压缩经典生成对抗网络 Hybrid Quantum-classical Compressed Generative Adversarial Networks Based on Matrix Product Operators 计算机科学, 2025, 52(6): 74-81. https://doi.org/10.11896/jsjkx.240500017 |
| [9] | 陈亚当, 高宇轩, 卢楚翰, 车洵. 基于显著性掩模混合的小样本图像分类 Saliency Mask Mixup for Few-shot Image Classification 计算机科学, 2025, 52(6): 256-263. https://doi.org/10.11896/jsjkx.240600123 |
| [10] | 孙晋永, 王雪纯, 蔡国永, 尚之量. 基于元增量学习的开放集识别方法 Open Set Recognition Based on Meta Class Incremental Learning 计算机科学, 2025, 52(5): 187-198. https://doi.org/10.11896/jsjkx.240600162 |
| [11] | 王一飞, 张胜杰, 薛迪展, 钱胜胜. 基于带毒分类器的自监督后门攻击防御方法 Self-supervised Backdoor Attack Defence Method Based on Poisoned Classifier 计算机科学, 2025, 52(4): 336-342. https://doi.org/10.11896/jsjkx.240100005 |
| [12] | 孙汤慧, 赵刚, 郭美倩. 大选择性核双边网络的长尾分布医学图像分类方法 Long-tail Distributed Medical Image Classification Based on Large Selective Nuclear Bilateral-branch Networks 计算机科学, 2025, 52(4): 231-239. https://doi.org/10.11896/jsjkx.240700039 |
| [13] | 熊其冰, 苗启广, 杨天, 袁本政, 费洋扬. 一种基于混合量子卷积神经网络的恶意代码检测方法 Malicious Code Detection Method Based on Hybrid Quantum Convolutional Neural Network 计算机科学, 2025, 52(3): 385-390. https://doi.org/10.11896/jsjkx.240800006 |
| [14] | 肖子勤, 史涯晴, 曲豫宾. 基于神经元覆盖指标的测试用例生成优化研究 Research on Optimization of Test Case Generation Based on Neuron Coverage Index 计算机科学, 2025, 52(11): 339-348. https://doi.org/10.11896/jsjkx.240900006 |
| [15] | 阮宁, 李淳, 马昊月, 贾异, 李涛. 量子元启发式算法及其应用综述 Review of Quantum-inspired Metaheuristic Algorithms and Its Applications 计算机科学, 2025, 52(10): 190-200. https://doi.org/10.11896/jsjkx.250500127 |
|
||
首页