Abstract
Feature representation is usually a key point in image recognition. The recognition performance can be potentially improved if the data distribution information is exploited. In this paper, we propose an image recognition approach based on generative score space. Specifically, we first leverage probabilistic latent semantic analysis (pLSA) to model the distribution of images. Then, we derive the mid-level feature from the model in a generative feature learning manner. At last, the derived feature is embedded into a discriminative classifier for image recognition. The advantages of our proposed approach are two folds. First, the probabilistic generative modeling allows us exploiting information hidden in data and has good adaptation to data distribution. Second, the discriminative learning process can utilize the information of label effectively. To confirm the effectiveness of our method, we perform image recognition on three datasets. The results demonstrate its advantages.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Jiang, Z., Zhang, S., Zeng, J.A.: Hybrid generative/discriminative method for semi-supervised classification. Knowl.-Based Syst. 37(2), 137–145 (2013)
Wang, B., Liu, Y.: Collaborative similarity metric learning for semantic image annotation and retrieval. KSII Trans. Internet Inf. Syst. 7(5), 1252–1271 (2013)
Wang, C., Wang, B., Zheng, L.: Learning free energy kernel for image retrieval. KSII Trans. Internet Inf. Syst. 8(8), 2895–2912 (2014)
Zhou, X., Jiang, P., Wang, X.: Recognition of control chart patterns using fuzzy SVM with a hybrid kernel function. J. Intell. Manuf., 1–17 (2015)
Moran, S., Lavrenko, V.: A sparse kernel relevance model for automatic image annotation. Int. J. Multimedia Inf. Retriev. 3(4), 209–229 (2014)
Sadeghi, M.A., Farhadi, A.: Recognition using visual phrases. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1745–1752 (2011)
Bouguila, N.: Hybrid generative/discriminative approaches for proportional data modeling and classification. IEEE Trans. Knowl. Data Eng. 24(12), 2184–2202 (2012)
Wang, B., Li, X., Liu, Y.: Learning discriminative fisher kernel for image retrieval. KSII Trans. Internet Inf. Syst. 7(3), 532–548 (2013)
Jaakkola, T.S., Haussler, D.: Exploiting generative models in discriminative classifiers. Adv. Neural. Inf. Process. Syst. 11(11), 487–493 (1998)
Wang, B., Wang, C., Liu, Y.: Exploiting class label in generative score spaces. Neurocomputing 145(18), 495–504 (2014)
Perina, A., Cristani, M., Castellani, U., Murino, V., Jojic, N.: Free energy score spaces: Using generative information in discriminative classifiers. IEEE Trans. Softw. Eng. 34(7), 1249–1262 (2012)
Chatfield, K., Lempitsky, V., Vedaldi, A., Zisserman, A.: The devil is in the details: an evaluation of recent feature encoding methods. In: Proceedings of British Machine Vision Conference, pp. 76.1–76.12 (2011)
Carreira, J., Caseiro, R., Batista, J., Sminchisescu, C.: Free-form region description with second-order pooling. IEEE Trans. Pattern Anal. Mach. Intell. 37(6), 1177–1189 (2015)
Cinbis, R.G., Verbeek, J., Schmid, C.: Approximate fisher kernels of non-iid image models for image categorization. IEEE Trans. Pattern Anal. Mach. Intell., 1 (2015)
Li, X., Wang, B., Liu, Y., Tai, S.L.: Stochastic feature mapping for pac-bayes classification. Mach. Learn. 101, 5–33 (2015)
Jordan, M.I., Ghahramani, Z., Jaakkola, T.S., Saul, L.K.: An introduction to variational methods for graphical models. Mach. Learn. 37(2), 183–233 (2012)
Nen, M., Alpaydin, E.: Localized multiple kernel learning. In: Proceedings of International Conference on Machine Learning, pp. 1531–1565 (2008)
Feng, J., Ni, B., Tian, Q., Yan, S.: Geometric lp-norm feature pooling for image classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2697–2704 (2011)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Computer Science, pp. 580–587 (2014)
Mennesson, J., Saint-Jean, C., Mascarilla, L.: Color fourier-mellin descriptors for image recognition. Pattern Recogn. Lett. 40(1), 27–35 (2014)
Chen, J., Li, Q., Peng, Q., Wong, K.H.: Csift based locality-constrained linear coding for image classification. Formal Pattern Anal. Appl. 18(2), 441–450 (2015)
Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Computer Vision and Pattern Recognition, pp. 3128–3137. IEEE (2015)
Dixit, M., Rasiwasia, N., Vasconcelos, N.: Adapted gaussian models for image classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 937–943 (2011)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Comput. Sci. 11(11), 487–493 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. Comput. Sci. (2015)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep fisher networks for large-scale image classification. In: Advances in Neural Information Processing Systems, pp. 163–171 (2013)
Zhang, C., Liu, J., Tian, Q., Xu, C., Lu, H., Ma, S.: Image classification by non-negative sparse coding, low-rank and sparse decomposition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1673–1680 (2011)
Poczos, B., Xiong, L., Sutherland, D.J., Schneider, J.: Nonparametric kernel estimators for image classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2989–2996 (2012)
Seidenari, L., Serra, G., Bagdanov, A.D., Del Bimbo, A.: Local pyramidal descriptors for image recognition. IEEE Trans. Pattern Anal. Mach. Intell. 36(5), 1 (2013)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (2000)
Acknowledgments
This work was supported by the National Natural Science Foundation of China (No. 61503251), the Science and Technology Commission of Shanghai Municipality (No. 16070502900), the Program of Shanghai Normal University (No. A-7001-15-001005).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, B., Li, C., Li, X., Mao, H. (2017). A Hybrid Generative-Discriminative Learning Algorithm for Image Recognition. In: Fei, M., Ma, S., Li, X., Sun, X., Jia, L., Su, Z. (eds) Advanced Computational Methods in Life System Modeling and Simulation. ICSEE LSMS 2017 2017. Communications in Computer and Information Science, vol 761. Springer, Singapore. https://doi.org/10.1007/978-981-10-6370-1_46
Download citation
DOI: https://doi.org/10.1007/978-981-10-6370-1_46
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6369-5
Online ISBN: 978-981-10-6370-1
eBook Packages: Computer ScienceComputer Science (R0)