基于深度残差网络图像分类算法研究综述
作者:
基金项目:

中国科学院科技服务网络计划区域重点项目(Y82E01,KFJ-STS-QYZD-058);国家研发基础设施和设施发展计划(DKA2018-12-02-XX);中国科学院战略性先导科技专项(XDA19060205);中科院信息化专项(XXH13505-03-205,XXH13506-305,XXH13506-303);中国科学院计算机网络信息中心一三五规划重点培育方向(CNIC-PY-1408,CNIC_PY_1409);专项大熊猫国际合作资金


Survey on Image Classification Algorithms Based on Deep Residual Network
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [36]
  • |
  • 相似文献 [20]
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    近年来,由于计算机技术的飞速迅猛发展,特别是硬件条件的改善,计算能力不断提高,深层神经网络训练的时间大大缩短,深度残差网络也迅速成为一个新的研究热点.深度残差网络作为一种极深的网络架构,在精度和收敛等方面都展现出了很好的特性.研究者们深入研究其本质并在此基础上提出了很多关于深度残差网络的改进,如宽残差网络,金字塔型残差网络,密集型残差网络,注意力残差网络等等.本文从残差网络的设计出发,分析了不同残差单元的构造方式,介绍了深度残差网络不同的变体.从不同的角度比较了不同网络之间的差异以及这些网络架构在常用图像分类数据集上的性能表现.最后我们对于这些网络进行了总结,并讨论了未来深度残差网络在图像分类领域的一些研究方向.

    Abstract:

    Recently, the training time of deep neural network has been greatly shortened because of the rapid development of computer technology especially the improvement of hardware conditions. The deep residual network has rapidly become a new research hotspot. The architecture exhibits good features in terms of precision and convergence. Researchers have delved into its nature and proposed many improvements on deep residual networks, such as wide residual networks, deep pyramidal residual networks, densely residual networks, attention residual network, etc. This study analyzes the construction of different residual units from the design of residual network, and introduces different variants of deep residual network. From different aspects, We compare the differences between different networks and the performance of these network architectures on common image classification datasets. Finally, we summarize these networks and discuss some research directions of future deep residual networks in the field of image classification.

    参考文献
    [1] 温煌璐. 基于卷积神经网络的图像分类算法研究[硕士学位论文]. 乌鲁木齐:新疆大学, 2018.
    [2] 郭玥秀, 杨伟, 刘琦, 等. 残差网络研究综述. 计算机应用研究, 1-8. https://doi.org/10.19734/j.issn.1001-3695.2018.12.0922.[2019-10-27].
    [3] 张帆, 张良, 刘星, 等. 基于深度残差网络的脱机手写汉字识别研究. 计算机测量与控制, 2017, 25(12):259-262
    [4] 陈晨, 刘明明, 刘兵, 等. 基于残差网络的图像超分辨率重建算法. 计算机工程与应用:1-8. http://kns.cnki.net/kcms/detail/11.2127.TP.20190527.1720.009.html.[2019-10-27].
    [5] 马慧. 基于卷积神经网络的图像分类技术及应用[硕士学位论文]. 江门:五邑大学, 2018.
    [6] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, NV, USA. 2012. 1097-1105.
    [7] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556v1, 2014.
    [8] Wu ZF, Shen CH, Van Den Hengel A. Wider or deeper:Revisiting the ResNet model for visual recognition. Pattern Recognition, 2019, 90:119-133. doi:10.1016/j.patcog.2019.01.006
    [9] Szegedy C, Liu W, Jia YQ, et al. Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA. 2015. 1-9.
    [10] He KM, Zhang XY, Ren SQ, et al. Identity mappings in deep residual networks. In:Leibe B, Matas J, Sebe N, et al., eds. Computer Vision-ECCV 2016. Cham:Springer, 2016. 630-645.
    [11] He KM, Zhang XY, Ren SQ, et al. Deep residual learning for image recognition. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA. 2016. 770-778.
    [12] 杨雨浓. 基于深度学习的人脸表情识别方法研究[博士学位论文]. 杨凌:西北大学, 2017.
    [13] 宋伟, 纳鹏宇, 刘宁宁. 基于双目视觉系统的运动目标跟踪算法研究. 北京交通大学学报, 2013, 37(6):13-17, 26. doi:10.3969/j.issn.1673-0291.2013.06.003
    [14] 苏松志, 李绍滋, 陈淑媛, 等. 行人检测技术综述. 电子学报, 2012, 40(4):814-820. doi:10.3969/j.issn.0372-2112.2012.04.031
    [15] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA. 2015. 3431-3440.
    [16] 王灿辉, 张敏, 马少平. 自然语言处理在信息检索中的应用综述. 中文信息学报, 2007, 21(2):35-45. doi:10.3969/j.issn.1003-0077.2007.02.006
    [17] Ioffe S. Batch renormalization:Towards reducing minibatch dependence in batch-normalized models. Advances in Neural Information Processing Systems, 2017:1942-1950
    [18] Han D, Kim J, Kim J. Deep pyramidal residual networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA. 2017. 6307-6315.
    [19] Hoffer E, Ailon N. Deep metric learning using triplet network. Proceedings of International Workshop on Similarity-Based Pattern Recognition. Copenhagen, Denmark. 2015. 84-92.
    [20] Zhang CY, Bengio S, Singer Y. Are all layers created equal? arXiv:1902.01996, 2019.
    [21] Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA. 2017. 2261-2269.
    [22] Wang F, Jiang MQ, Qian C, et al. Residual attention network for image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA. 2017. 6450-6458.
    [23] Zagoruyko S, Komodakis N. Wide residual networks. arXiv:1605.07146, 2016.
    [24] Veit A, Wilber MJ, Belongie S. Residual networks behave like ensembles of relatively shallow networks. Advances in Neural Information Processing Systems. San Francisco, CA, USA. 2016.550-558.
    [25] Huang G, Sun Y, Liu Z, et al. Deep networks with stochastic depth. Proceedings of the 14th European Conference on Computer Vision. Amsterdam, The Netherlands:Springer, 2016. 646-661.
    [26] Lin M, Chen Q, Yan SC. Network in network. arXiv:1312.4400v3, 2013.
    [27] Krizhevsky A, Hinton G. Convolutional deep belief networks on CIFAR-10. Unpublished Manuscript, 2010. https://www.cs.toronto.edu/~kriz/conv-cifar10-aug2010.pdf.
    [28] Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. 2818-2826.
    [29] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout:A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 2014, 15:1929-1958
    [30] Xie S, Girshick R, Dollár P, et al. Aggregated residual transformations for deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA. 2017. 5987-5995.
    [31] Gastaldi X. Shake-shake regularization. arXiv:1705.07485, 2017.
    [32] Zhang K, Sun M, Han TX, et al. Residual networks of residual networks:Multilevel residual networks. IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28(6):1303-1314. doi:10.1109/TCSVT.2017.2654543
    [33] Yamada Y, Iwamura M, Kise K. Deep pyramidal residual networks with separated stochastic depth. arXiv:1612.01230, 2016.
    [34] Hu J, Shen L, Sun G. Squeeze-and-excitation networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA. 2018. 7132-7141.
    [35] Woo S, Park J, Lee JY, et al. CBAM:Convolutional block attention module. Proceedings of the 15th European Conference on Computer Vision. Munich, Germany. 2018. 3-19.
    [36] Tan MX, Le QV. EfficientNet:Rethinking model scaling for convolutional neural networks. arXiv:1905.11946, 2019.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

赵志成,罗泽,王鹏彦,李健.基于深度残差网络图像分类算法研究综述.计算机系统应用,2020,29(1):14-21

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2019-06-20
  • 最后修改日期:2019-07-16
  • 在线发布日期: 2019-12-30
  • 出版日期: 2020-01-15
文章二维码
您是第11482586位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号