Abstract
The convolutional neural network (CNN) is an effective machine learning model which has been successfully used in the computer vision tasks such as image recognition and object detection. The pooling step is an important process in the CNN to decrease the dimensionality of the input image data and keep the transformation invariance for preventing the overfitting problem. There are two major pooling methods, i.e. the max pooling and the average pooling. Their performances depend on the data and the features to be extracted. In this study, we propose a hybrid system of the two pooling methods to improve the feature extraction performance. We randomly choose one of them for each pooling zone with a fixed probability. We show that the hybrid pooling method (HPM) enhances the generalization ability of the CNNs in numerical experiments with the handwritten digit images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Cogn. Model. 5(3), 1 (1988)
Hinton, G.E., Srivastava, N., Krizhevsky, A., et al.: Improving neural networks by preventing co-adaptation of feature detectors (2012)
Srivastava, N., Hinton, G., Krizhevsky, A., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Zeiler, M.D., Fergus, R.: Stochastic pooling for regularization of deep convolutional neural networks. In: ICLR (2013)
Wu, H., Gu, X.: Max-pooling dropout for regularization of convolutional neural networks. In: Arik, S., Huang, T., Kin Lai, T., Liu, Q. (eds.) Neural Information Processing, vol. 9486, pp. 46–54. Springer, Cham (2015)
Boureau, Y.L., Ponce, J., LeCun, Y.: A theoretical analysis of feature pooling in visual recognition. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 111–118 (2010)
Goodfellow, I.J., Warde-Farley, D., Mirza, M., et al.: Maxout networks. In: Proceedings of International Conference on Machine Learning (ICML) (2013)
Wan, L., Zeiler, M., Zhang, S., et al.: Regularization of neural networks using dropconnect. In: Proceedings of the 30th International Conference on Machine Learning, ICML-13, pp. 1058–1066 (2013)
Cha, K.H., Hadjiiski, L., Samala, R.K., et al.: Urinary bladder segmentation in CT urography using deep-learning convolutional neural network and level sets. Med. Phys. 43(4), 1882–1896 (2016)
Wolterink, J.M., Leiner, T., de Vos, B.D., et al.: Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks. Med. Image Anal. (2016)
Acknowledgments
This work was partially supported by the Otsuka Toshimi Scholarship Foundation (ZT) and JSPS KAKENHI Grant Number 16K00326 (GT).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Tong, Z., Aihara, K., Tanaka, G. (2016). A Hybrid Pooling Method for Convolutional Neural Networks. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science(), vol 9948. Springer, Cham. https://doi.org/10.1007/978-3-319-46672-9_51
Download citation
DOI: https://doi.org/10.1007/978-3-319-46672-9_51
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46671-2
Online ISBN: 978-3-319-46672-9
eBook Packages: Computer ScienceComputer Science (R0)