An Incremental Deep Learning Network for On-line Unsupervised Feature Extraction

  • Yu Liang
  • Yi Yang
  • Furao ShenEmail author
  • Jinxi Zhao
  • Tao Zhu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10635)


In this paper, we propose an incremental deep learning network for on-line unsupervised feature extraction. This deep learning network is based on 3 data processing components: (1) cascaded incremental orthogonal component analysis network (IOCANet); (2) binary hashing; and (3) blockwise histograms. In this architecture, IOCANet can process online data and get filters to do convolutions. Binary hashing is used to enhance the nonlinearity of IOCANet and reduce the quantity of the data. Eventually, the data is encoded by blockwise histograms. Experiments demonstrate that the proposed architecture has potential results for on-line unsupervised feature extraction.


Deep learning On-line unsupervised feature extraction 



This work is supported in part by the National Science Foundation of China under Grant Nos. (61373130, 61375064, 61373001), and Jiangsu NSF grant (BK20141319).


  1. 1.
    Kavukcuoglu, K., Sermanet, P., Boureau, Y.L., et al.: Learning convolutional feature hierarchies for visual recognition. In: International Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, pp. 1090–1098. Curran Associates Inc. (2010)Google Scholar
  2. 2.
    Tao, Z., Ye, X., Furao, S., et al.: An online incremental orthogonal component analysis method for dimensionality reduction. Neural Netw. 85, 33–50 (2016)Google Scholar
  3. 3.
    Chan, T.H., Jia, K., Gao, S., et al.: PCANet: a simple deep learning baseline for image classification? IEEE Trans. Image Process. 24(12), 5017–5032 (2015). A Publication of the IEEE Signal Processing SocietyCrossRefMathSciNetGoogle Scholar
  4. 4.
    Dan, C., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3642–3649. IEEE Computer Society (2012)Google Scholar
  5. 5.
    Yu, K., Lin, Y., Lafferty, J.: Learning image representations from the pixel level via hierarchical sparse coding. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1713–1720. IEEE Computer Society (2011)Google Scholar
  6. 6.
    Salve, S.G., Jondhale, K.C.: Shape matching and object recognition using shape contexts. In: IEEE International Conference on Computer Science and Information Technology, pp. 471–474. IEEE (2010)Google Scholar
  7. 7.
    Keysers, D., Deselaers, T., Gollan, C., et al.: Deformation models for image recognition. IEEE Trans. Pattern Anal. Mach. Intell. 29, 1422–1435 (2007)CrossRefGoogle Scholar
  8. 8.
    Lee, H., Grosse, R., Ranganath, R., et al.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: International Conference on Machine Learning, pp. 609–616. ACM (2009)Google Scholar
  9. 9.
    Zeiler, M.D., Fergus, R.: Stochastic Pooling for Regularization of Deep Convolutional Neural Networks. Eprint Arxiv (2013)Google Scholar
  10. 10.
    Goodfellow, I.J., Wardefarley, D., Mirza, M., et al.: Maxout networks. Comput. Sci. 28, 1319–1327 (2013)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Yu Liang
    • 1
  • Yi Yang
    • 1
  • Furao Shen
    • 1
    Email author
  • Jinxi Zhao
    • 1
  • Tao Zhu
    • 1
  1. 1.National Key Laboratory for Novel Software Technology, Department of Computer Science and Technology, Collaborative Innovation Center of Novel Software Technology and IndustrializationNanjing UniversityNanjingChina

Personalised recommendations