Abstract
Extracting informative regularized representations of input signals plays a key role in the field of artificial intelligence, such as machine learning and robotics. Traditional approaches feature \(\ell _2\) norm and sparse inducing \(\ell _p\) norm (\(0 \le p \le 1\)) based optimization methods, imposing strict regularization on the representations. However, these approaches overlook the fact that signals and atoms in the overcomplete dictionaries usually contain such wealth of structural information that could improves representations. This paper systematically exploits data manifold geometric structure where signals and atoms reside in, and thus presents a principled extension of sparse coding, i.e. two-layers local coordinate coding, which demonstrates a high dimensional nonlinear function could be locally approximated by a global linear function with quadratic approximation power. Moreover, to learn each latent layer, corresponding patterned optimization approaches are developed, encoding distance information between signals and atoms into the representations. Experimental results demonstrate the significance of this extension on improving the image classification performance and its potential applications for object recognition in robot system are also exploited.
This work is supported by National Natural Science Foundation of China (NSFC, No. 61340046), National High Technology Research and Development Program of China (863 Program, No. 2006AA04Z247), Scientific and Technical Innovation Commission of Shenzhen Municipality (No. JCYJ20130331144631730).
Chapter PDF
Similar content being viewed by others
References
Donoho, D.L.: Compressed sensing. IEEE Transactions on Information Theory 52(4), 1289–1306 (2006)
Aharon, M., Elad, M., Bruckstein, A.: K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on Signal Processing 54(11), 4311–4322 (2006)
Kouskouridas, R., Charalampous, K., Gasteratos, A.: Sparse pose manifolds. Autonomous Robots 37(2), 191–207 (2014)
Yu, K., Zhang, T., Gong, Y.: Nonlinear learning using local coordinate coding. In: Advances in Neural Information Processing Systems, pp. 2223–2231 (2009)
Yu, K., Zhang, T.: Improved local coordinate coding using local tangents. In: Proceedings of the 27th International Conference on Machine Learning, pp. 1215–1222 (2010)
Lin, Y., Tong, Z., Zhu, S., Yu, K.: Deep coding network. In: Advances in Neural Information Processing Systems, pp. 1405–1413 (2010)
Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3360–3367 (2010)
Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(6), 643–660 (2001)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. Computer Vision and Image Understanding 106(1), 59–70 (2007)
Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence 31(2), 210–227 (2009)
Jiang, Z., Lin, Z., Davis, L.S.: Learning a discriminative dictionary for sparse coding via label consistent k-svd. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1697–1704 (2011)
Qiu, Q., Patel, V.M., Chellappa, R.: Information-theoretic dictionary learning for image classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 36(11), 2173–2184 (2014)
Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural computation 15(6), 1373–1396 (2003)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)
Fan, M., Zhang, X., Lin, Z., Zhang, Z., Bao, H.: A regularized approach for geodesic-based semisupervised multimanifold learning. IEEE Transactions on Image Processing 23(5), 2133–2147 (2014)
Oliveira, G.L., Nascimento, E.R., Vieira, A.W.: Montenegro Campos, M.F.: Sparse spatial coding: A novel approach to visual recognition. IEEE Transactions on Image Processing 23(6), 2719–2731 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xiao, W., Liu, H., Tang, H., Liu, H. (2015). Two-layers Local Coordinate Coding. In: Zha, H., Chen, X., Wang, L., Miao, Q. (eds) Computer Vision. CCCV 2015. Communications in Computer and Information Science, vol 546. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-48558-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-662-48558-3_4
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-48557-6
Online ISBN: 978-3-662-48558-3
eBook Packages: Computer ScienceComputer Science (R0)