Advertisement

Hybrid Networks: Improving Deep Learning Networks via Integrating Two Views of Images

  • Sunny Verma
  • Wei LiuEmail author
  • Chen Wang
  • Liming Zhu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11301)

Abstract

The principal component analysis network (PCANet) is an unsupervised parsimonious deep network, utilizing principal components as filters in the layers. It creates an amalgamated view of the data by transforming it into column vectors which destroys its spatial structure while obtaining the principal components. In this research, we first propose a tensor-factorization based method referred as the Tensor Factorization Networks (TFNet). The TFNet retains the spatial structure of the data by preserving its individual modes. This presentation provides a minutiae view of the data while extracting matrix factors. However, the above methods are restricted to extract a single representation and thus incurs information loss. To alleviate this information loss with the above methods we propose Hybrid Network (HybridNet) to simultaneously learn filters from both the views of the data. Comprehensive results on multiple benchmark datasets validate the superiority of integrating both the views of the data in our proposed HybridNet.

Keywords

Tensor decomposition Classification Feature extraction 

References

  1. 1.
    Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013)CrossRefGoogle Scholar
  2. 2.
    Broadhurst, R.E.: Statistical estimation of histogram variation for texture classification. In: Proceedings International Workshop on Texture Analysis and Synthesis, pp. 25–30 (2005)Google Scholar
  3. 3.
    Bruna, J., Mallat, S.: Invariant scattering convolution networks. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1872–1886 (2013)CrossRefGoogle Scholar
  4. 4.
    Chan, T.H., Jia, K., Gao, S., Lu, J., Zeng, Z., Ma, Y.: PCANet: a simple deep learning baseline for image classification? IEEE Trans. Image Process. 24(12), 5017–5032 (2015)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Cichocki, A., et al.: Tensor decompositions for signal processing applications: from two-way to multiway component analysis. IEEE Sig. Process. Mag. 32(2), 145–163 (2015)CrossRefGoogle Scholar
  6. 6.
    Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 215–223 (2011)Google Scholar
  7. 7.
    Cong, F., Lin, Q.H., Kuang, L.D., Gong, X.F., Astikainen, P., Ristaniemi, T.: Tensor decomposition of EEG signals: a brief review. J. Neurosci. Methods 248, 59–69 (2015)CrossRefGoogle Scholar
  8. 8.
    Crosier, M., Griffin, L.D.: Using basic image features for texture classification. Int. J. Comput. Vision 88(3), 447–460 (2010)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: LIBLINEAR: a library for large linear classification. J. Mach. Learn. Res. 9(Aug), 1871–1874 (2008)zbMATHGoogle Scholar
  10. 10.
    Grauman, K., Darrell, T.: The pyramid match kernel: discriminative classification with sets of image features. In: Tenth IEEE International Conference on Computer Vision 2005, ICCV 2005, vol. 2, pp. 1458–1465. IEEE (2005)Google Scholar
  11. 11.
    Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. In: ICLR (2016)Google Scholar
  12. 12.
    Hayman, E., Caputo, B., Fritz, M., Eklundh, J.-O.: On the significance of real-world conditions for material classification. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 253–266. Springer, Heidelberg (2004).  https://doi.org/10.1007/978-3-540-24673-2_21CrossRefGoogle Scholar
  13. 13.
    Huang, J., Yuan, C.: FANet: factor analysis neural network. In: Arik, S., Huang, T., Lai, W.K., Liu, Q. (eds.) ICONIP 2015. LNCS, vol. 9491, pp. 172–181. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-26555-1_20CrossRefGoogle Scholar
  14. 14.
    Kossaifi, J., Khanna, A., Lipton, Z., Furlanello, T., Anandkumar, A.: Tensor contraction layers for parsimonious deep nets. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1940–1946. IEEE (2017)Google Scholar
  15. 15.
    Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Master’s thesis, Department of Computer Science, University of Toronto (2009)Google Scholar
  16. 16.
    Larochelle, H., Erhan, D., Courville, A., Bergstra, J., Bengio, Y.: An empirical evaluation of deep architectures on problems with many factors of variation. In: Proceedings of the 24th International Conference on Machine Learning, pp. 473–480. ACM (2007)Google Scholar
  17. 17.
    Lin, M., Chen, Q., Yan, S.: Network in network. In: ICLR (2013)Google Scholar
  18. 18.
    Ngiam, J., Chen, Z., Chia, D., Koh, P.W., Le, Q.V., Ng, A.Y.: Tiled convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1279–1287 (2010)Google Scholar
  19. 19.
    Rifai, S., Vincent, P., Muller, X., Glorot, X., Bengio, Y.: Contractive auto-encoders: explicit invariance during feature extraction. In: Proceedings of the 28th International Conference on International Conference on Machine Learning, pp. 833–840. Omnipress (2011)Google Scholar
  20. 20.
    Savas, B., Eldén, L.: Handwritten digit classification using higher order singular value decomposition. Pattern Recogn. 40(3), 993–1003 (2007)CrossRefGoogle Scholar
  21. 21.
    Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: Advances in Neural Information Processing Systems, pp. 2951–2959 (2012)Google Scholar
  22. 22.
    Sohn, K., Lee, H.: Learning invariant representations with local transformations. In: Proceedings of the 29th International Conference on Machine Learning, pp. 1339–1346 (2012)Google Scholar
  23. 23.
    Sohn, K., Zhou, G., Lee, C., Lee, H.: Learning and selecting features jointly with point-wise gated Boltzmann machines. In: International Conference on Machine Learning, pp. 217–225 (2013)Google Scholar
  24. 24.
    Varma, M., Zisserman, A.: A statistical approach to material classification using image patch exemplars. IEEE Trans. Pattern Anal. Mach. Intell. 31(11), 2032–2047 (2009)CrossRefGoogle Scholar
  25. 25.
    Vasilescu, M.A.O., Terzopoulos, D.: Multilinear image analysis for facial recognition. In: 2002 Proceedings 16th International Conference on Pattern Recognition, vol. 2, pp. 511–514. IEEE (2002)Google Scholar
  26. 26.
    Zheng, L., Yang, Y., Tian, Q.: Sift meets CNN: a decade survey of instance retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 40(5), 1224–1244 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Advanced Analytics Institute, School of SoftwareUniversity of Technology SydneySydneyAustralia
  2. 2.CSIRO, Data61SydneyAustralia

Personalised recommendations