Abstract
This paper investigates the problem of image classification with limited or no annotations, but abundant unlabelled data. We propose the DBP (Differential-weighted Global Optimum of BP Neural Network) to make the performance of the BP Neural Network to become more stable. In details, the optimal weights will be saved as potential global optimum during the process of iteration and then we combine the BP Neural Network with the potential global weights to adjust parameters in the backward feedback process for the first time. As the model has fallen into local optimization, we replace the present parameters with the potential global optimal weights to optimize our model. Besides, we consider EP, CNN, SIFT image features and conduct several experiments on eight standard datasets. The results show that DBP mostly outperforms other supervised and semi-supervised learning methods in the state of the art.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Coates, A., Ng, A.Y., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. J. Mach. Learn. Res. 15, 215–223 (2011)
Dosovitskiy, A., Springenberg, J., Riedmiller, M., Brox, T.: Discriminative unsupervised feature learning with convolutional neural networks. In: Neural Information Processing System, Montreal, Canada, pp. 766–774, December 2014
Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: International Conference on Computer Vision, Santiago, Chile, pp. 1422–1430, December 2015
Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: Computer Science (2015)
Fergus, R., Weiss, Y., Torralba, A.: Semi-supervised learning in gigantic image collections. In: Neural Information Processing System, Vancouver, Canada, pp. 522–530, December 2009
Guillaumin, M., Verbeek, J.J., Schmid, C.: Multi-model semi-supervised learning for image classification. In: IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, America, pp. 902–909, June 2010
Dai, D., Van Gool, L.: Ensemble projection for semi-supervised image classification. In: International Conference on Computer Vision, Sydney, Australia, pp. 2072–2079, December 2013
Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A.: Discovering objects and their location in images. In: International Conference on Computer Vision, Beijing, China, pp. 370–377, October 2005
Dai, D., Wu, T., Zhu, S.C.: Discovering scene categories by information projection and cluster sampling. In: IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, America, pp. 483–497, June 2010
Chapelle, O., Schölkopf, B., Zien, A., et al.: Semi-Supervised Learning. MIT Press, Cambridge (2006)
Elgammal, A., Lee, C.S.: Separating style and content on a nonlinear manifold. In: Computer Vision and Pattern Recognition, Washington, DC, America, pp. 478–485, June 2004
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Zhu, P., Zhang, L., Zuo, W., Zhang, D.: From point to set: extend the learning of distance metrics. In: International Conference on Computer Vision, Sydney, Australia, pp. 2664–2671, December 2013
Huang, G.B., Lee, H., Learned-Miller, E.: Learning hierarchical representations for face verification with convolutional deep belief networks. In: Computer Vision Pattern Recognition, Providence, Rhode Island, pp. 2518–2525, June 2012
Dai, D., Gool, L.V.: Unsupervised high-level feature learning by ensemble projection for semi-supervised image classification and image clustering. In: Computer Vision & Pattern Recognition, Las Vegas, America, pp. 254–260, June 2016
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25(2), 1097–1105 (2012)
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., et al.: DeCAF: a deep convolutional activation feature for genetic visual recognition. Comput. Sci. 50(1), 815–830 (2014)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, Columbus, America, pp. 580–587, June 2014
Lazebnik, S., Schmid, C., Ponce, J.: A sparse texture representation using local affine regions. IEEE Pattern Anal. Mach. Intell. 27(8), 1265–1278 (2005)
Li, F.F., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: IEEE Conference on Computer Vision and Pattern Recognition, Washington DC, USA, pp. 59–70, June 2004
Coates, A., Ng, A.Y., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. Int. Conf. Artif. Intell. Stat. 15, 215–223 (2011)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: IEEE Conference on Computer Vision and Pattern Recognition, New York, USA, pp. 17–22, June 2006
Quattoni, A., Torralba, A.: Recognizing indoor scenes, In: IEEE Conference on Computer Vision and Pattern Recognition, Florida, USA, pp. 413–420, June 2009
Li, L.J., Li, F.F.: What, where, and who? Classifying event by scene and object recognition. In: International Conference on Computer Vision, Rio de Janeiro, Brazil, pp. 1–8, October 2007
Xu, Z., Tao, D., Zhang, Y., Wu, J., Tsoi, A.: Architectural style classification using multinomial latent logistic regression, European Conference on Computer Vision, Zurich, Swiss, pp. 600–615, September 2014
Yang, Y., Newsam, S.: Bag-of-visual-words and spatial extensions for land-use classification. In: International Conference on Advances in Geographic Information Systems, pp. 270–279. ACM, San Jose, November 2010
Acknowledgement
The research was partly supported by the program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning, USST incubation project (15HJPY-MS02), National Natural Science Foundation of China (No. U1304616, No.61502220). We would like to appreciate Zhong hui for modifying English spelling during the whole work.
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
Ma, L., Lin, X., Jiang, L. (2017). Differential-Weighted Global Optimum of BP Neural Network on Image Classification. In: Kim, K., Joukov, N. (eds) Information Science and Applications 2017. ICISA 2017. Lecture Notes in Electrical Engineering, vol 424. Springer, Singapore. https://doi.org/10.1007/978-981-10-4154-9_63
Download citation
DOI: https://doi.org/10.1007/978-981-10-4154-9_63
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-4153-2
Online ISBN: 978-981-10-4154-9
eBook Packages: EngineeringEngineering (R0)