KSII Transactions on Internet and Information Systems (TIIS)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

An Extended Generative Feature Learning Algorithm for Image Recognition

  • Wang, Bin (College of Information, Mechanical and Electrical Engineering, Shanghai Normal University) ;
  • Li, Chuanjiang (College of Information, Mechanical and Electrical Engineering, Shanghai Normal University) ;
  • Zhang, Qian (College of Information, Mechanical and Electrical Engineering, Shanghai Normal University) ;
  • Huang, Jifeng (College of Information, Mechanical and Electrical Engineering, Shanghai Normal University)
  • Received : 2017.03.31
  • Accepted : 2017.06.16
  • Published : 2017.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Image recognition has become an increasingly important topic for its wide application. It is highly challenging when facing to large-scale database with large variance. The recognition systems rely on a key component, i.e. the low-level feature or the learned mid-level feature. The recognition performance can be potentially improved if the data distribution information is exploited using a more sophisticated way, which usually a function over hidden variable, model parameter and observed data. These methods are called generative score space. In this paper, we propose a discriminative extension for the existing generative score space methods, which exploits class label when deriving score functions for image recognition task. Specifically, we first extend the regular generative models to class conditional models over both observed variable and class label. Then, we derive the mid-level feature mapping from the extended models. At last, the derived feature mapping is embedded into a discriminative classifier for image recognition. The advantages of our proposed approach are two folds. First, the resulted methods take simple and intuitive forms which are weighted versions of existing methods, benefitting from the Bayesian inference of class label. Second, the probabilistic generative modeling allows us to exploit hidden information and is well adapt to data distribution. To validate the effectiveness of the proposed method, we cooperate our discriminative extension with three generative models for image recognition task. The experimental results validate the effectiveness of our proposed approach.

Keywords

References

  1. Jiang Z, Zhang S, Zeng J. A, "hybrid generative/discriminative method for semi-supervised classification," Knowledge-Based Systems, vol. 37, no. 2, pp. 137-145, 2013. https://doi.org/10.1016/j.knosys.2012.07.020
  2. B. Wang and Y. Liu, "Collaborative similarity metric learning for semantic image annotation and retrieval," Ksii Transactions on Internet and Information Systems, vol. 7, no. 5, pp. 1252-1271, 2013. https://doi.org/10.3837/tiis.2013.05.018
  3. C.Wang, B.Wang, and L. Zheng, "Learning free energy kernel for image retrieval," Ksii Transactions on Internet and Information Systems, vol. 8, no. 8, pp. 2895-2912, 2014. https://doi.org/10.3837/tiis.2014.08.019
  4. Zhou X, Jiang P, Wang X, "Recognition of control chart patterns using fuzzy SVM with a hybrid kernel function," Journal of Intelligent Manufacturing, pp. 1-17, 2015.
  5. Moran S, Lavrenko V, "A sparse kernel relevance model for automatic image annotation," International Journal of Multimedia Information Retrieval, vol. 3, no. 4, pp. 209-229, 2014. https://doi.org/10.1007/s13735-014-0063-y
  6. M. A. Sadeghi and A. Farhadi, "Recognition using visual phrases," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1745-1752, 2011.
  7. Bouguila N, "Hybrid Generative/Discriminative Approaches for Proportional Data Modeling and Classification," IEEE Transactions on Knowledge & Data Engineering, vol. 24, no. 12, pp. 2184-2202, 2012. https://doi.org/10.1109/TKDE.2011.162
  8. A Perina, M. Cristani, U. Castellani, V. Murino, N. Jojic, "Free energy score spaces: using generative information in discriminative classifiers," IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011.
  9. X. Li, S. L. Tai and Y. Liu, "Hybrid generative-discriminative classification using posterior divergence," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2713-2720, 2011.
  10. T. Jebara, R. Kondor, A. Howard, "Probability product kernels," Journal of Machine Learning Research, vol. 5, pp. 819-844, 2004.
  11. N. Vasconcelos, "On the efficient evaluation of probabilistic similarity functions for image retrieval," IEEE Transactions on Information Theory, vol. 50, no. 7, pp. 1482-1496, 2004. https://doi.org/10.1109/TIT.2004.830760
  12. Wang B, Wang C, Liu Y, "Exploiting class label in generative score spaces," Neurocomputing, vol. 145, no. 18, pp. 495-504, 2014. https://doi.org/10.1016/j.neucom.2014.05.004
  13. X. Li, B.Wang, Y. Liu, and S. L. Tai, "Stochastic feature mapping for pac-bayes classification," Machine Learning, vol. 101, pp. 5-33, 2015. https://doi.org/10.1007/s10994-015-5525-9
  14. B. Wang, X. Li and Y. Liu, "Learning discriminative fisher kernel for image retrieval," Ksii Transactions on Internet and Information Systems, vol. 7, no. 3, pp. 532-548, 2013.
  15. T. S. Jaakkola and D. Haussler, "Exploiting generative models in discriminative classifiers," Advances in Neural Information Processing Systems, vol. 11, no. 11, pp. 487-493, 1998.
  16. Amer M R, Siddiquie B, Tamrakar A, et al., "Human Social Interaction Modeling Using Temporal Deep Networks," Computer Science, vol. 351, no. 2, pp. 193-197, 2015.
  17. Wang B, Wang C, Huang J, "Multiple Clusters Parts-based Sparse Representation for Single Example Face Identification," Journal of Visual Communication & Image Representation, vol. 40, pp. 237-250, 2016. https://doi.org/10.1016/j.jvcir.2016.06.019
  18. K. Chatfield, V. Lempitsky, A. Vedaldi, and A. Zisserman, "The devil is in the details: an evaluation of recent feature encoding methods," in Proc. of British Machine Vision Conference, pp. 76.1-76.12, 2011.
  19. J. Carreira, R. Caseiro, J. Batista, and C. Sminchisescu, "Free-form region description with second-order pooling," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 6, pp. 1177-1189, 2015. https://doi.org/10.1109/TPAMI.2014.2361137
  20. M. I. Jordan, Z. Ghahramani, T. S. Jaakkola, and L. K. Saul, "An introduction to variational methods for graphical models," Machine Learning, vol. 37, no. 2, pp. 183-233, 2012. https://doi.org/10.1023/A:1007665907178
  21. K.Tsuda, M.Kawanabe, G.Ratsch, S.Sonnenburg, K.Muller, "A new discriminative kernel from probabilistic models," Neural Computing, vol. 14, no. 10, pp. 2397-2414, 2002. https://doi.org/10.1162/08997660260293274
  22. R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," Computer Science, pp. 580-587, 2014.
  23. Jin W, Ping L, Mary F H S, et al., "Biomedical time series clustering based on non-negative sparse coding and probabilistic topic model," Computer Methods & Programs in Biomedicine, vol. 111, no. 3, pp. 629-41, 2013. https://doi.org/10.1016/j.cmpb.2013.05.022
  24. Mennesson J, Saint-Jean C, Mascarilla L, "Color Fourier-Mellin Descriptors for Image Recognition," Pattern Recognition Letters, vol. 40, no. 1, pp. 27-35, 2014. https://doi.org/10.1016/j.patrec.2013.12.014
  25. J. Chen, Q. Li, Q. Peng, and K. H.Wong, "Csift based locality-constrained linear coding for image classification," Formal Pattern Analysis and Applications, vol. 18, no. 2, pp. 441-450, 2015. https://doi.org/10.1007/s10044-014-0427-1
  26. Zhang T, Ghanem B, Liu S, et al., "Low-Rank Sparse Coding for Image Classification," in Proc. of IEEE International Conference on Computer Vision, pp. 281-288, 2013.
  27. Yang X, Zhang T, Xu C, "Locality discriminative coding for image classification," in Proc. of International Conference on Internet Multimedia Computing and Service, pp. 52-55, 2013.
  28. K. Chatfield, V. Lempitsky, A. Vedaldi and A. Zisserman, "The devil is in the details: an evaluation of recent feature encoding methods," in Proc. of British Machine Vision Conference, 2011.
  29. B. Poczos, L. Xiong, D. J. Sutherland, and J. Schneider, "Nonparametric kernel estimators for image classification," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2989-2996, 2012.
  30. J.Yang, K.Yu, Y.Gong, T.Huang, "Linear spatial pyramid matching using sparse coding for image classification," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, 2009.
  31. C.Zhang, J.Liu, Q.Tian, C.Xu, H.Lu, S.Ma, "Image classification by non-negative sparse coding, low-rank and sparse decomposition," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp.1673-1680, 2011.
  32. M.Dixit, N.Rasiwasia, N.Vasconcelos, "Adapted Gaussian models for image classification," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp.937-943, 2011.
  33. Karpathy A, Fei-Fei L, "Deep visual-semantic alignments for generating image descriptions," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp. 3128-3137, 2015.
  34. K. Simonyan, and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," Computer Science, vol. 11, no. 11, pp. 487-493, 2014.
  35. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," Computer Science, 2015.
  36. Simonyan K, Vedaldi A, Zisserman A, "Deep Fisher Networks for Large-Scale Image Classification," Advances in Neural Information Processing Systems, pp. 163-171, 2013.
  37. C. Zhang, J. Liu, Q. Tian, C. Xu, H. Lu, and S. Ma, "Image classification by non-negative sparse coding, low-rank and sparse decomposition," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1673-1680, 2011.
  38. Lazebnik S, Schmid C, Ponce J, "Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories," in Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2169-2178, 2006.
  39. Wang J, Yang J, Yu K, et al. "Locality-constrained Linear Coding for image classification," in Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3360-3367, 2010.
  40. Boureau Y, Roux N L, Bach F, et al., "Ask the locals: Multi-way local pooling for image recognition," in Proc. of IEEE International Conference on Computer Vision, pp. 2651-2658, 2011.
  41. V.Vapnik, "The Nature of Statistical Learning Theory," Springer, Verlag, New York, 2000.
  42. M.Gonen, E.Alpaydin, "Localized multiple kernel learning," in Proc. of International Conference on Machine Learning, pp. 352-359, 2008.
  43. Blei D M, Ng A Y, Jordan M I, "Latent dirichlet allocation," Journal of Machine Learning Research, vol. 3, pp. 993-1022, 2003.