Convolutional Deep Networks for Visual Data Classification
- 644 Downloads
This paper develops a semi-supervised learning algorithm called convolutional deep networks (CDN), to address the image classification problem with deep learning. First, we construct the previous several hidden layers using convolutional restricted Boltzmann machines, which can reduce the dimension and abstract the information of the images effectively. Second, we construct the following hidden layers using restricted Boltzmann machines, which can abstract the information of images quickly. Third, the constructed deep architecture is fine-tuned by gradient-descent based supervised learning with an exponential loss function. CDN can reduce the dimension and abstract the information of the images at the same time efficiently. More importantly, the abstraction and classification procedure of CDN use the same deep architecture to optimize the same parameter in different steps continuously, which can improve the learning ability effectively. We did several experiments on two standard image datasets, and show that CDN are competitive with both representative semi-supervised classifiers and existing deep learning techniques.
KeywordsSemi-supervised learning Deep learning Convolutional neural networks Visual data classification
Unable to display preview. Download preview PDF.
- 1.Chapelle O, Scholkopf B, Zien A (2006) Semi-supervised learning. MIT Press, CambridgeGoogle Scholar
- 3.Desjardins G, Bengio Y (2008) Empirical evaluation of convolutional rbms for vision. Tech. repGoogle Scholar
- 11.Lee H, Grosse R, Ranganath R, Ng A (2009) Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: International conference on machine learning. ACM, Montreal, Canada, pp 609–616Google Scholar
- 12.Li F, Fergus R, Perona P (2004) Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. In: CVPR workshop on generative-model based vision. Elsevier Science Inc., New York, pp 1–9Google Scholar
- 14.Machajdik J, Hanbury A (2010) Affective image classification using features inspired by psychology and art theory. In: International conference on multimedia. ACM, New York, pp 83–92Google Scholar
- 15.Salakhutdinov R, Hinton GE (2007) Learning a nonlinear embedding by preserving class neighbourhood structure. J Mach Learn Res 2: 412–419Google Scholar
- 16.Weston J, Ratle F, Collobert R (2008) Deep learning via semi-supervised embedding. In: International conference on machine learning. ACM, Helsinki, pp 1168–1175Google Scholar
- 17.Zhu X (2007) Semi-supervised learning literature survey. Tech. rep.. University of Wisconsin Madison, MadisonGoogle Scholar