Locality and Sparsity Preserving Embedding Convolutional Neural Network for Image Classification

  • Yu Xia
  • Yongzhao ZhanEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11935)


Convolutional neural networks (CNN) combined with manifold structures have attracted much attention, because they preserve local manifolds that are crucial and effective to reflect the intrinsic structure of data. In view of the excellent performance in image classification of CNN and the success in dimensionality reduction of manifold learning. This paper proposes a new deep learning framework based on deep CNN for image classification, which is called Locality and Sparsity Preserving Embedding Convolutional Neural Network (LSPE-CNN), that simultaneously considers the local information and natural sparsity of data into deep CNN. Compared to existing models, our proposed framework not only better preserve the associated features in the dataset, but also tries to seek the reconstruction relationship among samples by combining different manifold learning methods embedded in the CNN model, which further enhances the feature representation ability of the network. Experiments on CIFAR-10 and CIFAR-100 for image classification indicate that the proposed framework is superior to the other methods proposed in the deep learning literature.


Convolutional neural networks Feature representation Manifold learning Image classification 



This work was supported by the National Natural Science Foundation of China (No. 61672268) and the Primary Research & Development Plan of Jiangsu Province (No. BE2015137).


  1. 1.
    Ahonen, T., Hadid, A., Pietikainen, M.: Face description with local binary patterns: application to face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 12, 2037–2041 (2006)CrossRefGoogle Scholar
  2. 2.
    Bai, C., Huang, L., Chen, J., Pan, X., Chen, S.: Optimization of deep convolutional neural network for large scale image classification. Ruan Jian Xue Bao/J. Softw. 29(4), 137–146 (2018)zbMATHGoogle Scholar
  3. 3.
    Cai, D., He, X., Zhou, K., Han, J., Bao, H.: Locality sensitive discriminant analysis. IJCAI 2007, 1713–1726 (2007)Google Scholar
  4. 4.
    Cireşan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. arXiv preprint arXiv:1202.2745 (2012)
  5. 5.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: International Conference on Computer Vision & Pattern Recognition (CVPR’05), vol. 1, pp. 886–893. IEEE Computer Society (2005)Google Scholar
  6. 6.
    Fang, J., Zhan, Y., Shen, X.: Multi-graph regularized deep auto-encoders for multi-view image representation. In: Hong, R., Cheng, W.-H., Yamasaki, T., Wang, M., Ngo, C.-W. (eds.) PCM 2018. LNCS, vol. 11164, pp. 797–807. Springer, Cham (2018). Scholar
  7. 7.
    Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence And Statistics, pp. 315–323 (2011)Google Scholar
  8. 8.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  9. 9.
    He, X., Niyogi, P.: Locality preserving projections. In: Advances in Neural Information Processing Systems, pp. 153–160 (2004)Google Scholar
  10. 10.
    Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
  12. 12.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  13. 13.
    Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)
  14. 14.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRefGoogle Scholar
  15. 15.
    Malinowski, M., Fritz, M.: Learnable pooling regions for image classification. arXiv preprint arXiv:1301.3516 (2013)
  16. 16.
    Qiao, L., Chen, S., Tan, X.: Sparsity preserving projections with applications to face recognition. Pattern Recogn. 43(1), 331–341 (2010)CrossRefGoogle Scholar
  17. 17.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)Google Scholar
  18. 18.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)CrossRefGoogle Scholar
  19. 19.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  20. 20.
    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
  21. 21.
    Srivastava, N., Salakhutdinov, R.R.: Discriminative transfer learning with tree-based priors. In: Advances in Neural Information Processing Systems, pp. 2094–2102 (2013)Google Scholar
  22. 22.
    Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)Google Scholar
  23. 23.
    Yang, H.F., Lin, K., Chen, C.S.: Supervised learning of semantics-preserving hash via deep convolutional neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 40(2), 437–451 (2018)CrossRefGoogle Scholar
  24. 24.
    Yuan, Y., Mou, L., Lu, X.: Scene recognition by manifold regularized deep learning architecture. IEEE Trans. Neural Netw. Learn. Syst. 26(10), 2222–2233 (2015)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Zeiler, M.D., Fergus, R.: Stochastic pooling for regularization of deep convolutional neural networks. arXiv preprint arXiv:1301.3557 (2013)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Computer Science and Communication EngineeringJiangsu UniversityZhenjiangChina

Personalised recommendations