卷积神经网络池化方法综述
Survey on Convolutional Neural Network Pooling Methods
DOI: 10.12677/SEA.2020.95041, PDF,  被引量    科研立项经费支持
作者: 袁铭阳, 胡志颖, 李 颖：北京信息科技大学计算机学院，北京；周长胜, 黄宏博*：北京信息科技大学计算机学院，北京；北京信息科技大学计算智能研究所，北京
关键词: 卷积神经网络；池化方法；池化层；Convolutional Neural Network； Pooling Method； Pooling Layer
摘要: 池化层是卷积神经网络的重要组成部分，池化层通过池化计算对经过卷积层后的特征图进行降维。随着卷积神经网络的发展，产生了许多新的池化方法代替传统的池化方法，在多类任务中取得了突破性进展。本文针对基于卷积神经网络的池化方法进行综述，对池化方法进行了分类，详细阐述了各种新的池化方法相较于传统池化方法的改进之处，介绍了池化方法的具体计算方法，并且对各种池化方法的效果进行了对比，最后给出了池化方法在主流数据集上的性能指标。
Abstract: The pooling layer is an important part of convolution neural network. The pooling layer reduces the dimension of the feature map after convolution layer through pool calculation. With the de-velopment of convolutional neural network, many new pooling methods have been produced to replace the traditional pooling methods, and a breakthrough has been made in many kinds of tasks. This paper summarizes the pooling methods based on convolution neural network, classifies the pooling methods, describes the improvements of various new pooling methods compared with the traditional pooling methods, introduces the specific calculation methods of pooling methods, and compares the effects of various pooling methods, and finally gives the performance indicators of pooling methods on the mainstream datasets.
文章引用：袁铭阳, 周长胜, 黄宏博, 胡志颖, 李颖. 卷积神经网络池化方法综述[J]. 软件工程与应用, 2020, 9(5): 360-372. https://doi.org/10.12677/SEA.2020.95041

参考文献

[1] Rippel, O., Snoek, J. and Adams, R.P. (2015) Spectral Representations for Convolutional Neural Networks. Advances in Neural Information Processing Systems 28 (NIPS 2015), 2449-2457.
[2] Zhang, H. and Ma, J. (2018) Hartley Spectral Pooling for Deep Learning. arXiv Preprint arXiv: 1810.04028.
[3] Lin, T.Y., Roychowdhury, A. and Maji, S. (2015) Bilinear CNN Models for Fine-Grained Visual Recognition. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 1449-1457. [Google Scholar] [CrossRef] 
[4] Li, X., Yang, C., Chen, S., et al. (2019) Semantic Bilinear Pooling for Fine-Grained Recognition. arXiv:1904.01893.
[5] Kek, X.Y., Chin, C.S. and Li, Y. (2019) Acoustic Scene Clas-sification Using Bilinear Pooling on Time-Liked and Frequency-Liked Convolution Neural Network. 2019 IEEE Sym-posium Series on Computational Intelligence (SSCI), Xiamen, 6-9 December 2019, 3189-3194. [Google Scholar] [CrossRef] 
[6] Gao, Y., Beijbom, O., Zhang, N. and Darrell, T. (2016) Compact Bilinear Pooling. 2016 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 317-326. [Google Scholar] [CrossRef] 
[7] Li, P., Xie, J., Wang, Q., et al. (2018) Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization. 2018 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 947-955. [Google Scholar] [CrossRef] 
[8] Acharya, D., Huang, Z., Panipaudel, D., et al. (2018) Covariance Pooling for Facial Expression Recognition. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, 18-22 June 2018, 480-4807. [Google Scholar] [CrossRef] 
[9] Ionescu, C., Vantzos, O. and Sminchisescu, C. (2015) Matrix Backpropagation for Deep Networks with Structured Layers. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 2965-2973. [Google Scholar] [CrossRef] 
[10] Sermanet, P., Chintala, S. and LeCun, Y. (2012) Convolutional Neural Networks Applied to House Numbers Digit Classification. Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), 3288-3291.
[11] Hyvärinen, A. and Köster, U. (2007) Complex Cell Pooling and the Statistics of Natural Images. Network: Computation in Neural Systems, 18, 81-100. [Google Scholar] [CrossRef] [PubMed]
[12] Zeiler, M.D. and Fergus, R. (2013) Stochastic Pooling for Regularization of Deep Convolutional Neural Networks arXiv Preprint arXiv: 1301.3557.
[13] Zhai, S., Wu, H., Kumar, A., et al. (2017) S3pool: Pooling with Stochastic Spatial Sampling. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 4003-4011. [Google Scholar] [CrossRef] 
[14] Yu, D., Wang, H., Chen, P., et al. (2014) Mixed Pooling for Con-volutional Neural Networks. In: Miao, D., Pedrycz, W., Ślȩzak, D., Peters, G., Hu, Q. and Wang, R., Eds., International Conference on Rough Sets and Knowledge Technology, Springer, Cham, 364-375. [Google Scholar] [CrossRef] 
[15] Hyun, J., Seong, H. and Kim, E. (2019) Universal Pool-ing—A New Pooling Method for Convolutional Neural Networks. arXiv:1907.11440.
[16] Shi, Z.L., Ye, Y.D. and Wu, Y.P. (2016) Rank-Based Pooling for Deep Convolutional Neural Networks. Neural Networks, 83, 21-31.
[17] Murray, N. and Perronnin, F. (2014) Generalized Max Pooling. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 2473-2480.
[18] Christlein, V., Spranger, L., Seuret, M., et al. (2019) Deep Generalized Max Pooling. 2019 International Conference on Document Analysis and Recognition (ICDAR), Sydney, 20-25 September 2019, 1090-1096.
[19] Graham, B. (2014) Fractional Max-Pooling. arXiv:1412.6071.
[20] Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012) Imagenet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, 1097-1105.
[21] He, K., Zhang, X., Ren, S., et al. (2015) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 1904-1916. [Google Scholar] [CrossRef] 
[22] Asgari, R., Waldstein, S., Schlanitz, F., et al. (2019) U-Net with Spatial Pyramid Pooling for Drusen Segmentation in Optical Coherence Tomography. In: Fu, H., Garvin, M., MacGillivray, T., Xu, Y. and Zheng, Y., Eds., International Workshop on Ophthalmic Medical Image Analysis, Springer, Cham, 77-85. [Google Scholar] [CrossRef] 
[23] Lin, M., Chen, Q. and Yan, S. (2013) Network in Network. arXiv Preprint arXiv:1312.4400.
[24] Gong, Y., Wang, L., Guo, R., et al. (2014) Multi-Scale Orderless Pooling of Deep Convolutional Activation Features. In: Fleet, D., Pajdla, T., Schiele, B. and Tuytelaars, T., Eds., Computer Vi-sion—ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, Springer, Cham, 392-407. [Google Scholar] [CrossRef] 
[25] Sun, Y.X., Sun, C., Wang, D., et al. (2019) ROI Pooled Cor-relation Filters for Visual Tracking. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 5776-5784. [Google Scholar] [CrossRef] 
[26] Girshick, R. (2015) Fast R-CNN. 2015 IEEE International Con-ference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 1440-1448. [Google Scholar] [CrossRef] 
[27] Krizhevsky, A. and Hinton, G. (2009) Learning Multiple Layers of Features from Tiny Images. 7.

为你推荐