• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Bagging deep convolutional autoencoders trained with a mixture of real data and GAN-generated data


Abstract

While deep neural networks have achieved remarkable performance in representation learning, a huge amount of labeled training data are usually required by supervised deep models such as convolutional neural networks. In this paper, we propose a new representation learning method, namely generative adversarial networks (GAN) based bagging deep convolutional autoencoders (GAN-BDCAE), which can map data to diverse hierarchical representations in an unsupervised fashion. To boost the size of training data, to train deep model and to aggregate diverse learning machines are the three principal avenues towards increasing the capabilities of representation learning of neural networks. We focus on combining those three techniques. To this aim, we adopt GAN for realistic unlabeled sample generation and bagging deep convolutional autoencoders (BDCAE) for robust feature learning. The proposed method improves the discriminative ability of learned feature embedding for solving subsequent pattern recognition problems. We evaluate our approach on three standard benchmarks and demonstrate the superiority of the proposed method compared to traditional unsupervised learning methods.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
C. Hu, X. Wu and Z. Shu, "Bagging deep convolutional autoencoders trained with a mixture of real data and GAN-generated data," KSII Transactions on Internet and Information Systems, vol. 13, no. 11, pp. 5427-5445, 2019. DOI: 10.3837/tiis.2019.11.009.

[ACM Style]
Cong Hu, Xiao-Jun Wu, and Zhen-Qiu Shu. 2019. Bagging deep convolutional autoencoders trained with a mixture of real data and GAN-generated data. KSII Transactions on Internet and Information Systems, 13, 11, (2019), 5427-5445. DOI: 10.3837/tiis.2019.11.009.