Abstract
PCANet is a simple deep learning baseline for image classification, which learns the filters banks by PCA instead of stochastic gradient descent (SGD) in each layer. It shows a good performance for image classification tasks with only a few parameters and no backpropagation procedure. However, PCANet suffers from two main problems. The first problem is the features explosion which limits its depth to two layers. The second issue is the binarization process which leads to discriminative information loss. To handle these problems, we adopted CNN-like convolution layers to learn the PCA filter-bank and reduce the number of dimensions. We also used second-order pooling with z-score normalization to replace the histogram descriptor. The late fusion method is used to combine the class posteriors generated each layer. The proposed network has been tested on image classification tasks including MNIST, Cifar10, Cifar100 and Tiny ImageNet databases. The experimental results show that our model achieves better performance than standard PCANet and is competitive with some CNN methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Low, C.Y., Teoh, A.B.-J., Toh, K.-A.: Stacking PCANet+: an overly simplified convnets baseline for face recognition. IEEE Signal Process. Lett. 24(11), 1581–1585 (2017)
Chan, T.-H., et al.: PCANet: a simple deep learning baseline for image classification? IEEE Trans. Image Process. 24(12), 5017–5032 (2015)
Yu, K., Salzmann, M.: Statistically-motivated second-order pooling. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)
Wang, Q., et al.: Deep CNNs meet global covariance pooling: better representation and generalization. arXiv preprint arXiv:1904.06836 (2019)
Carreira, J., Caseiro, R., Batista, J., Sminchisescu, C.: Semantic segmentation with second-order pooling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7578, pp. 430–443. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33786-4_32
Mao, Y., Wang, R., Shan, S., Chen, X.: COSONet: compact second-order network for video face recognition. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 51–67. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20893-6_4
Wang, Q., et al.: RAID-G: robust estimation of approximate infinite dimensional Gaussian with application to material recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Liu, Yu., Guo, Y., Georgiou, T., Lew, M.S.: Fusion that matters: convolutional fusion networks for visual recognition. Multimedia Tools Appl. 77(22), 29407–29434 (2018). https://doi.org/10.1007/s11042-018-5691-4
Ergun, H., et al.: Early and late level fusion of deep convolutional neural networks for visual concept recognition. Int. J. Semant. Comput. 10(03), 379–397 (2016)
Ebersbach, M., Herms, R., Eibl, M.: Fusion methods for ICD10 code classification of death certificates in multilingual corpora. In: CLEF (Working Notes), September 2017
Fan, C., et al.: PCANet-II: when PCANet meets the second order pooling. IEICE Trans. Inf. Syst. 101(8), 2159–2162 (2018)
Zeiler, M.D., Fergus, R.: Stochastic pooling for regularization of deep convolutional neural networks. arXiv preprint arXiv:1301.3557 (2013)
Goodfellow, I., et al.: Maxout networks. In: International Conference on Machine Learning. PMLR (2013)
Lin, M., et al.: Network in network. arXiv preprint arXiv:1312.4400 (2013)
Springenberg, J.T., Dosovitskiy, A., Brox, T., Ried-miller, M.: Striving for simplicity: the all convolutional net. arXiv preprint arXiv:1412.6806 (2014)
Larsson, G., Maire, M., Shakhnarovich, G.: FractalNet: ultra-deep neural networks without residuals. arXiv preprint arXiv:1605.07648 (2016)
Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646–661. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_39
Huang, G., et al.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
Krizhevsky, A., et al.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)
Ng, C.J., Teoh, A.B.J.: DCTNet: a simple learning-free approach for face recognition. In: 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA). IEEE (2015)
Xi, M., et al.: Local binary pattern network: a deep learning approach for face recognition. In: 2016 IEEE international conference on Image processing. IEEE (2016)
Zhang, Y., Geng, T., Wu, X., Zhou, J., Gao, D.: ICANet: a simple cascade linear convolution network for face recognition. EURASIP J. Image Video Process. 2018(1), 1–7 (2018). https://doi.org/10.1186/s13640-018-0288-4
Wu, D., et al.: Kernel principal component analysis network for image classification. arXiv preprint arXiv:1512.06337 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv: 1409.1556 (2014)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
LeCun, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Abai, Z., Rajmalwar, N.: DenseNet models for tiny imagenet classification. arXiv preprint arXiv:1904.10429 (2019)
Fan, R.-E., et al.: LIBLINEAR: a library for large linear classification. J. Mach. Learn. Res. 9, 1871–1874 (2008)
Krizhevsky, A., et al.: Learning multiple layers of features from tiny images (2009)
Qaraei, M., et al.: Randomized non-linear PCA networks. Inf. Sci. 545, 241–253 (2021)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Alotaibi, M., Wilson, R.C. (2021). Multi-layer PCA Network for Image Classification. In: Torsello, A., Rossi, L., Pelillo, M., Biggio, B., Robles-Kelly, A. (eds) Structural, Syntactic, and Statistical Pattern Recognition. S+SSPR 2021. Lecture Notes in Computer Science(), vol 12644. Springer, Cham. https://doi.org/10.1007/978-3-030-73973-7_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-73973-7_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73972-0
Online ISBN: 978-3-030-73973-7
eBook Packages: Computer ScienceComputer Science (R0)