基于卷积神经网络的图像分类深度学习模型综述

doi:10.3778/j.issn.1002-8331.2411-0196

摘要/Abstract

摘要： 使用神经网络模型进行图像分类任务一直是非常重要的研究方向，随着深度学习技术的发展，对神经网络模型的要求也越来越高。在识别率高的同时，对模型的参数量、训练时间也都有较高的要求。卷积神经网络一直是深度学习中针对图像处理的主流方法，主要介绍基于卷积神经网络的分类模型的发展历程，分析其不同阶段各个模型的搭建思路；介绍Transformer与卷积神经网络结合的相关模型以及各模型在其他领域的应用情况。最后，对卷积神经网络的发展进行了探讨。

关键词: 卷积神经网络, 深度学习, 图像分类, Transformer

Abstract: Using neural network model for classification has always been a very important research direction. With the development of deep learning technology, the requirement for neural network model is getting higher and higher. At the same time, high recognition rate, the number of parameters and training time of the model are also highly required. Convolutional neural networks have always been the mainstream method for image classification in deep learning. This paper mainly introduces the development history of convolutional neural networks for classification model, and analyzes the construction ideas of each model at different stages. Secondly, the paper reviews relevant examples of Transformer combined with convolutional neural networks as well as the application of each model in other fields. Finally, the possible development directions of convolutional neural networks are discussed.

Key words: convolutional neural networks, deep learning, image classification, Transformer

刘鸿达, 孙旭辉, 李沂滨, 韩琳, 张宇. 基于卷积神经网络的图像分类深度学习模型综述[J]. 计算机工程与应用, 2025, 61(11): 1-21.

LIU Hongda, SUN Xuhui, LI Yibin, HAN Lin, ZHANG Yu. Review of Deep Learning Models for Image Classification Based on Convolutional Neural Networks[J]. Computer Engineering and Applications, 2025, 61(11): 1-21.

参考文献

[1] XU R S, CHEN C J, TU Z Z, et al. V2X-ViTV2: improved vision transformers for vehicle-to-everything cooperative perception[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, 47(1): 650-662.
[2] HU Y, HUANG Z A, LIU R, et al. Source free semi-supervised transfer learning for diagnosis of mental disorders on fMRI scans[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(11): 13778-13795.
[3] WEYLER J, MAGISTRI F, MARKS E, et al. PhenoBench: a large dataset and benchmarks for semantic image interpretation in the agricultural domain[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(12): 9583-9594.
[4] 张文生. 对人工智能现在和未来的思考[J]. 广西科学, 2021, 28(3): 209-214.
ZHANG W S. Thoughts on the future and present of artificial intelligence[J]. Guangxi Sciences, 2021, 28(3): 209-214.
[5] ACKLEY D H, HINTON G E, SEJNOWSKI T J. A learning algorithm for Boltzmann machines[J]. Cognitive Science, 1985, 9(1): 147-169.
[6] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[7] GU J X, WANG Z H, KUEN J, et al. Recent advances in convolutional neural networks[J]. Pattern Recognition, 2018, 77: 354-377.
[8] 张野, 李明超, 韩帅. 基于岩石图像深度学习的岩性自动识别与分类方法[J]. 岩石学报, 2018, 34(2): 333-342.
ZHANG Y, LI M C, HAN S. Automatic identification and classification in lithology based on deep learning in rock images[J]. Acta Petrologica Sinica, 2018, 34(2): 333-342.
[9] LIU D H, LI J, YUAN Q Q. A spectral grouping and attention-driven residual dense network for hyperspectral image super-resolution[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(9): 7711-7725.
[10] REN Z D, TANG Y Q, HE Z W, et al. Ship detection in high-resolution optical remote sensing images aided by saliency
information[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-16.
[11] LI D, WU H J, WANG Y J, et al. Lightweight parallel octave convolutional neural network for hyperspectral image classification[J]. Photogrammetric Engineering & Remote Sensing, 2023, 89(4): 233-243.
[12] SUN Y N, XUE B, ZHANG M J, et al. Evolving deep convolutional neural networks for image classification[J]. IEEE Transactions on Evolutionary Computation, 2020, 24(2): 394-407.
[13] 孔令军, 王茜雯, 包云超, 等. 基于深度学习的医疗图像分割综述[J]. 无线电通信技术, 2021, 47(2): 121-130.
KONG L J, WANG X W, BAO Y C, et al. A survey on medical image segmentation based on deep learning[J]. Radio Communications Technology, 2021, 47(2): 121-130.
[14] 田锦, 袁家政, 刘宏哲. 基于实例分割的车道线检测及自适应拟合算法[J]. 计算机应用, 2020, 40(7): 1932-1937.
TIAN J, YUAN J Z, LIU H Z. Instance segmentation based lane line detection and adaptive fitting algorithm[J]. Journal of Computer Applications, 2020, 40(7): 1932-1937.
[15] QU Y X, ZHANG C Y, YANG X B, et al. Classifying clear air echoes via static and motion streams network[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 19: 1-5.
[16] 张铮, 芦天亮, 曹金璇. 基于分割和多级掩膜学习的遮挡人脸识别方法[J]. 计算机科学与探索, 2024, 18(7): 1814-1825.
ZHANG Z, LU T L, CAO J X. Occluded face recognition based on segmentation and multi-stage mask learning[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(7): 1814-1825.
[17] 盛帅, 段先华, 胡维康, 等. Dynamic-YOLOX: 复杂背景下的苹果叶片病害检测模型 [J]. 计算机科学与探索, 2024, 18(8): 2118-2129.
SHENG S, DUAN X H, HU W K, et al.Dynamic-YOLOX:detection model for apple leaf disease in complex background[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(8): 2118-2129.
[18] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[19] 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.
[20] KHALID M, BABER J, KASI M K, et al. Empirical evaluation of activation functions in deep convolution neural network for facial expression recognition[C]//Proceedings of the 2020 43rd International Conference on Telecommunications and Signal Processing. Piscataway: IEEE, 2020: 204-207.
[21] LI T Y, ZHANG F, XIE G W, et al. A high speed reconfigurable architecture for softmax and GELU in vision transformer[J]. Electronics Letters, 2023, 59(5): e12751.
[22] HYUN J, SEONG H, KIM E. Universal pooling—a new pooling method for convolutional neural networks[J]. Expert Systems with Applications, 2021, 180: 115084.
[23] LIN S H, CAI L, LIN X M, et al. Masked face detection via a modified LeNet[J]. Neurocomputing, 2016, 218: 197-202.
[24] ELDEM H, üLKER E, IKL O Y. Alexnet architecture variations with transfer learning for classification of wound images[J]. Engineering Science and Technology, an International Journal, 2023, 45: 101490.
[25] SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 1-9.
[26] TANG P J, WANG H L, KWONG S. G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognition[J]. Neurocomputing, 2017, 225: 188-197.
[27] YAO X J, WANG X Y, KARACA Y, et al. Glomerulus classification via an improved GoogLeNet[J]. IEEE Access, 2020, 8: 176916-176923.
[28] FU Y S, SONG J, XIE F X, et al. Circular fruit and vegetable classification based on optimized GoogLeNet[J]. IEEE Access, 2021, 9: 113599-113611.
[29] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//Proceedings of the 3rd International Conference on Learning Representations, 2015.
[30] 30 D F, NGUYEN B M, ESPITIA H E. Towards automated eye cancer classification via VGG and ResNet networks using transfer learning[J]. Engineering Science and Technology, an International Journal, 2022, 35: 101214.
[31] LI Z G, LI B T, JAHNG S G, et al. Improved VGG algorithm for visual prosthesis image recognition[J]. IEEE Access, 2024, 12: 45727-45739.
[32] ABUHAYI B M, BEZABH Y A, AYALEW A M. Lumbar disease classification using an involutional neural based VGG nets (INVGG)[J]. IEEE Access, 2024, 12: 27518-27529.
[33] 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.
[34] XIE S N, GIRSHICK R, DOLLáR P, et al. Aggregated residual transformations for deep neural networks[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 5987-5995.
[35] HURTIK P, OZANA S. Dragonflies segmentation with U-Net based on cascaded ResNext cells[J]. Neural Computing and Applications, 2021, 33(9): 4567-4578.
[36] JAMPOUR M, ABBAASI S, JAVIDI M. CapsNet regularization and its conjugation with ResNet for signature identification[J]. Pattern Recognition, 2021, 120: 107851.
[37] DING X H, ZHANG X Y, MA N N, et al. RepVGG: making VGG-style ConvNets great again[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 13728-13737.
[38] SHI C J, HAN L L, ZHANG K, et al. Improved repvgg ground-based cloud image classification with attention convolution[J]. Atmospheric Measurement Techniques, 2024, 17: 979-997.
[39] TOUVRON H, BOJANOWSKI P, CARON M, et al. ResMLP: feedforward networks for image classification with data-efficient training[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(4): 5314-5321.
[40] LIU Z, MAO H Z, WU C Y, et al. A ConvNet for the 2020s[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 11966-11976.
[41] ZHU Y M, YUAN K X, ZHONG W L, et al. Spatial-spectral ConvNext for hyperspectral image classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16: 5453-5463.
[42] ZHANG L, DU J M, DONG S F, et al. AM-ResNet: low-energy-consumption addition-multiplication hybrid ResNet for pest recognition[J]. Computers and Electronics in Agriculture, 2022, 202: 107357.
[43] HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 2261-2269.
[44] YANG Y B, ZHONG Z S, SHEN T C, et al. Convolutional neural networks with alternately updated clique[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 2413-2422.
[45] CHEN B L, ZHAO T S, LIU J H, et al. Multipath feature recalibration DenseNet for image classification[J]. International Journal of Machine Learning and Cybernetics, 2021, 12(3): 651-660.
[46] WANG K, JIANG P, MENG J, et al. Attention-based DenseNet for pneumonia classification[J]. IRBM, 2022, 43(5): 479-485.
[47] WU Z T, XIAO M Q, FANG C, et al. Designing universally-approximating deep neural networks: a first-order optimization approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(9): 6231-6246.
[48] HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence. Piscataway: IEEE, 2020: 2011-2023.
[49] SHEN Z R, ZHANG M Y, ZHAO H Y, et al. Efficient attention: attention with linear complexities[C]//Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2021: 3530-3538.
[50] HUANG J, REN L F, ZHOU X K, et al. An improved neural network based on SENet for sleep stage classification[J]. IEEE Journal of Biomedical and Health Informatics, 2022, 26(10): 4948-4956.
[51] LIU Q H, LIU W K, LIU Y S, et al. Rice grains and grain impurity segmentation method based on a deep learning algorithm-NAM-EfficientNetV2[J]. Computers and Electronics in Agriculture, 2023, 209: 107824.
[52] DENG W J, MARSH J, GOULD S, et al. Fine-grained classification via categorical memory networks[J]. IEEE Transactions on Image Processing, 2022, 31: 4186-4196.
[53] KANG S Y, ZHANG Q L, WEI H R, et al. An efficient multiscale integrated attention method combined with hyperspectral system to identify the quality of rice with different storage periods and humidity[J]. Computers and Electronics in Agriculture, 2023, 213: 108259.
[54] YULDASHEV Y, MUKHIDDINOV M, ABDUSALOMOV A B, et al. Parking lot occupancy detection with improved MobileNetV3[J]. Sensors, 2023, 23(17): 7642.
[55] FAN S J, LIANG W, DING D R, et al. LACN: a lightweight attention-guided ConvNext network for low-light image enhancement[J]. Engineering Applications of Artificial Intelligence, 2023, 117: 105632.
[56] DONG X, LI D, FANG J D. FCCD-SAR: a lightweight SAR ATR algorithm based on FasterNet[J]. Sensors, 2023, 23(15): 6956.
[57] MAO Y Y, ZHANG N H, WANG Q, et al. Multi-level dispersion residual network for efficient image super-resolution[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2023: 1660-1669.
[58] QI J D, WANGDUI B B, JIANG J, et al. EDKSANet: an efficient dual-kernel split attention neural network for the classification of Tibetan medicinal materials[J]. Electronics, 2023, 12(20): 4330.
[59] PARK S, JEONG Y, CHOI Y S. Efficient dual attention transformer for image super-resolution[C]//Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing. New York: ACM, 2024: 963-970.
[60] NGO T T, HUH E N, HONG C S. ETANet: an efficient triple-attention network for salient object detection[C]//Proceedings of the 2023 International Conference on Information Networking. Piscataway: IEEE, 2023: 271-276.
[61] ZHOU L, CAI H M, GU J J, et al. Efficient image super-resolution using vast-receptive-field attention[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2023: 256-272.
[62] WANG T R, CHENG N, DING S J, et al. Efficient attention fusion feature extraction network for image super-resolution[C]//Proceedings of the 2023 7th International Conference on Deep Learning Technologies. New York: ACM, 2023: 35-44.
[63] LIU H Y, ZHANG Y Y, CHEN Y Y. A symmetric efficient spatial and channel attention (ESCA) module based on convolutional neural networks[J]. Symmetry, 2024, 16(8): 952.
[64] HOWARD A G, ZHU M, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications [J]. arXiv:1704.04861, 2017.
[65] SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 4510-4520.
[66] HOWARD A, SANDLER M, CHEN B, et al. Searching for MobileNetV3[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 1314-1324.
[67] MURTHY C B, HASHMI M F, KESKAR A G. Optimized MobileNet+SSD: a real-time pedestrian detection on a low-end edge device[J]. International Journal of Multimedia Information Retrieval, 2021, 10(3): 171-184.
[68] SANG X T, RUAN T, LI C L, et al. A real-time and high-performance MobileNet accelerator based on adaptive dataflow scheduling for image classification[J]. Journal of Real-Time Image Processing, 2023, 21(1): 4.
[69] QIU H M, YANG J M, JIANG J, et al. Mob-psp: modified MobileNet-V2 network for real-time detection of tomato diseases[J]. Journal of Real-Time Image Processing, 2024, 21(5): 181.
[70] JIANG T Y, LI L Y, SAMALI B, et al. Lightweight object detection network for multi-damage recognition of concrete bridges in complex environments[J]. Computer-Aided Civil and Infrastructure Engineering, 2024, 39(23): 3646-3665.
[71] TIAN X Y, SHI L W, LUO Y Q, et al. Garbage classification algorithm based on improved MobileNetV3[J]. IEEE Access, 2024, 12: 44799-44807.
[72] ZHANG Z, YANG X T, LUO N, et al. A novel method for Pu-erh tea face traceability identification based on improved MobileNetV3 and triplet loss[J]. Scientific Reports, 2023, 13(1): 6986.
[73] YANG Y H, HAN J. Real-Time object detector based MobileNetV3 for UAV applications[J]. Multimedia Tools and Applications, 2023, 82(12): 18709-18725.
[74] ZHANG X Y, ZHOU X Y, LIN M X, et al. ShuffleNet: an extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 6848-6856.
[75] MA N N, ZHANG X Y, ZHENG H T, et al. ShuffleNetV2: practical guidelines for efficient CNN architecture design[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2018: 122-138.
[76] RAN H H, WEN S P, WANG S Q, et al. Memristor-based edge computing of ShuffleNetV2 for image classification[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2021, 40(8): 1701-1710.
[77] CAO W, SHI Y, GUO X B, et al. BiInNet: bilateral inversion network for real-time velocity analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 1-17.
[78] ZHU Y L, LIU R, HU G, et al. Accurate identification of Cashmere and wool fibers based on enhanced ShuffleNetV2 and transfer learning[J]. Journal of Big Data, 2023, 10(1): 152.
[79] HE X J, JIN J, JIANG Y, et al. A lightweight convolutional neural network-based feature extractor for visible images[J]. Computer Vision and Image Understanding, 2024, 249: 104157.
[80] TAN M X, LE Q V. EfficientNet: rethinking model scaling for convolutional neural networks[C]//Proceedings of the 36th International Conference on Machine Learning, 2019: 6105-6114.
[81] SUHARJITO, ELWIREHARDJA G N, PRAYOGA J S. Oil palm fresh fruit bunch ripeness classification on mobile devices using deep learning approaches[J]. Computers and Electronics in Agriculture, 2021, 188: 106359.
[82] TAN M X, LE Q V. EfficientNetV2: smaller models and faster training[C]//Proceedings of the 38th International Conference on Machine Learning, 2021: 10096-10106.
[83] GUO M H, LU C Z, LIU Z N, et al. Visual attention network[J]. Computational Visual Media, 2023, 9(4): 733-752.
[84] JONSSON J, CHEESEMAN B L, MADDU S, et al. Parallel discrete convolutions on adaptive particle representations of images[J]. IEEE Transactions on Image Processing, 2022, 31: 4197-4212.
[85] CHEN J R, KAO S H, HE H, et al. Run, don’t walk: chasing higher FLOPs for faster neural networks[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 12021-12031.
[86] SUN M M, YAN C M. FGENet: a lightweight facial expression recognition algorithm based on FasterNet[J]. Signal, Image and Video Processing, 2024, 18(8): 5939-5956.
[87] LIN M B, CHEN B H, CHAO F, et al. Training compact CNNs for image classification using dynamic-coded filter fusion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(8): 10478-10487.
[88] LIU C Y, GAO G W, WU F, et al. An efficient feature reuse distillation network for lightweight image super-resolution[J]. Computer Vision and Image Understanding, 2024, 249: 104178.
[89] WEN L, GAO L, LI X Y, et al. A new genetic algorithm based evolutionary neural architecture search for image classification[J]. Swarm and Evolutionary Computation, 2022, 75: 101191.
[90] WOO S, DEBNATH S, HU R H, et al. ConvNestV2: co-designing and scaling ConvNets with masked autoencoders[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 16133-16142.
[91] PACAL I. MaxCerVixT: a novel lightweight vision transformer-based approach for precise cervical cancer detection[J]. Knowledge-Based Systems, 2024, 289: 111482.
[92] PACAL I. Enhancing crop productivity and sustainability through disease identification in maize leaves: exploiting a large dataset with an advanced vision transformer model[J]. Expert Systems with Applications, 2024, 238: 122099.
[93] WANG L G, GUO Y L, DONG X Y, et al. Exploring fine-grained sparsity in convolutional neural networks for efficient inference[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(4): 4474-4493.
[94] DUAN Z H, LU M, MA J, et al. QARV: quantization-aware ResNet VAE for lossy image compression[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(1): 436-450.
[95] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: transformers for image recognition at scale[J]. arXiv:2010.11929, 2020.
[96] BA L J, KIROS J R, HINTON G E. Layer normalization[J]. arXiv:1607.06450, 2016.
[97] HINTON G E, SRIVASTAVA N, KRIZHEVSKY A, et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. arXiv:1207.0580, 2012.
[98] WU H P, XIAO B, CODELLA N, et al. CvT: introducing convolutions to vision transformers[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 22-31.
[99] WANG W H, XIE E Z, LI X, et al. Pyramid vision transformer: a versatile backbone for dense prediction without convolutions[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 548-558.
[100] WANG W H, XIE E Z, LI X, et al. PVTV2: improved baselines with pyramid vision transformer[J]. Computational Visual Media, 2022, 8(3): 415-424.
[101] YE F M, WU K L, ZHANG R G, et al. Multi-scale feature fusion based on PVTv2 for deep hash remote sensing image retrieval[J]. Remote Sensing, 2023, 15(19): 4729.
[102] LIU Y, LI H H, CHENG J, et al. MSCAF-net: a general framework for camouflaged object detection via learning multi-scale context-aware features[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33(9): 4934-4947.
[103] LIU Z, LIN Y T, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 9992-10002.
[104] XUE D H, LEI T, YANG S M, et al. Triple change detection network via joint multifrequency and full-scale swin-transformer for remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1-15.
[105] ZHANG Y D, SHI Z L, WANG H, et al. LumVertCancNet: a novel 3D lumbar vertebral body cancellous bone location and segmentation method based on hybrid Swin-transformer[J]. Computers in Biology and Medicine, 2024, 171: 108237.
[106] LI W T, LIU W Y, ZHU J K, et al. Box2Mask: box-supervised instance segmentation via level-set evolution[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(7): 5157-5173.
[107] DUAN K W, BAI S, XIE L X, et al. CenterNet for object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(5): 3509-3521.
[108] GAO G W, XU Z X, LI J C, et al. CTCNet: a CNN-transformer cooperation network for face image super-resolution[J]. IEEE Transactions on Image Processing, 2023, 32: 1978-1991.
[109] YUAN L, HOU Q B, JIANG Z H, et al. VOLO: vision outlooker for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(5): 6575-6586.
[110] CHEN T S, MO L F. Swin-fusion: swin-transformer with feature fusion for human action recognition[J]. Neural Processing Letters, 2023, 55(8): 11109-11130.
[111] ZENG C, KWONG S, IP H. Dual swin-transformer based mutual interactive network for RGB-D salient object detection[J]. Neurocomputing, 2023, 559: 126779.
[112] CHITTA K, PRAKASH A, JAEGER B, et al. TransFuser: imitation with transformer-based sensor fusion for autonomous driving[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(11): 12878-12895.
[113] JIA Q, FENG X M, ZHANG W, et al. Bilevel progressive homography estimation via correlative region-focused transformer[J]. Computer Vision and Image Understanding, 2025, 250: 104209.
[114] LIU T, LI S X, XU M, et al. Assessing face image quality: a large-scale database and a transformer method[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(5): 3981-4000.
[115] KANG X D, DUAN P H, LI J E, et al. Efficient swin transformer for remote sensing image super-resolution[J]. IEEE Transactions on Image Processing, 2024, 33: 6367-6379.
[116] LIN M, CHEN M, ZHANG Y, et al. Super vision transformer[J]. International Journal of Computer Vision, 2023, 131(12): 3136-3151.
[117] MA J B, CHEN H. Efficient supervised pretraining of swin-transformer for virtual staining of microscopy images[J]. IEEE Transactions on Medical Imaging, 2024, 43(4): 1388-1399.
[118] SRINIVAS A, LIN T Y, PARMAR N, et al. Bottleneck transformers for visual recognition[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 16514-16524.
[119] MEHTA S, RASTEGARI M. MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer[C]//Proceedings of the 10th International Conference on Learning Representations, 2022.
[120] RASTEGARI S M A M. Separable self-attention for mobile vision transformers[J]. arXiv:2206.02680, 2022.
[121] WADEKAR S N, CHAURASIA A. MobileViTV3: mobile-friendly vision transformer with simple and effective fusion of local, global and input features[J]. arXiv:2209.15159, 2022.
[122] WANG Z W, WANG C Y, XU X W, et al. Quantformer: learning extremely low-precision vision transformers[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(7): 8813-8826.
[123] NIE X S, JIN H Y, YAN Y F, et al. ScopeViT: scale-aware vision transformer[J]. Pattern Recognition, 2024, 153: 110470.
[124] HU H J, LIANG M N, WANG C C, et al. Monocular depth estimation with boundary attention mechanism and shifted window adaptive bins[J]. Computer Vision and Image Understanding, 2024, 249: 104220.
[125] HUANG N C, YANG Y, ZHANG Q, et al. Lightweight cross-modal transformer for RGB-D salient object detection[J]. Computer Vision and Image Understanding, 2024, 249: 104194.
[126] WU G, JIANG J J, JIANG J P, et al. Transforming image super-resolution: a ConvFormer-based efficient approach[J]. IEEE Transactions on Image Processing, 2024, 33: 6071-6082.
[127] GIANG K T, SONG S, JO S. TopicFM+: boosting accuracy and efficiency of topic-assisted feature matching[J]. IEEE Transactions on Image Processing, 2024, 33: 6016-6028.
[128] TOUVRON H, CORD M, DOUZE M, et al. Training data-efficient image transformers & distillation through attention[C]//Proceedings of the International Conference on Machine Learning, 2021: 10347-10357.
[129] YANG C G, AN Z L, ZHOU H L, et al. Online knowledge distillation via mutual contrastive learning for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(8): 10212-10227.
[130] ZUO Y K, YAO H T, ZHUANG L S, et al. Hierarchical augmentation and distillation for class incremental audio-visual video recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(11): 7348-7362.
[131] CHOI H, JIN S, HAN K. Adversarial normalization: I can visualize everything (ICE)[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 12115-12124.
[132] CHOI H, JIN S, HAN K. ICEv2: interpretability, comprehensiveness, and explainability in vision transformer[J]. International Journal of Computer Vision, 2025, 133(5): 2487-2504.
[133] 郭朝鹏, 王馨昕, 仲昭晋, 等. 能耗优化的神经网络轻量化方法研究进展[J]. 计算机学报, 2023, 46(1): 85-102.
GUO C P, WANG X X, ZHONG Z J, et al. Research advance on neural network lightweight for energy optimization[J]. Chinese Journal of Computers, 2023, 46(1): 85-102.
[134] 吴凯, 沈文忠, 贾丁丁, 等. 融合Transformer和CNN的手掌静脉识别网络[J]. 计算机工程与应用, 2023, 59(24): 98-109.
WU K, SHEN W Z, JIA D D, et al. Palm vein recognition network combining transformer and CNN[J]. Computer Engineering and Applications, 2023, 59(24): 98-109.