![](/images/graphics-bg.png)
Information-Based Boundary Equilibrium Generative Adversarial Networks with Interpretable Representation Learning
Joint Authors
Hah, Junghoon
Lee, Woojin
Lee, Jaewook
Park, Saerom
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2018, Issue 2018 (31 Dec. 2018), pp.1-14, 14 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2018-10-17
Country of Publication
Egypt
No. of Pages
14
Main Subjects
Abstract EN
This paper describes a new image generation algorithm based on generative adversarial network.
With an information-theoretic extension to the autoencoder-based discriminator, this new algorithm is able to learn interpretable representations from the input images.
Our model not only adversarially minimizes the Wasserstein distance-based losses of the discriminator and generator but also maximizes the mutual information between small subset of the latent variables and the observation.
We also train our model with proportional control theory to keep the equilibrium between the discriminator and the generator balanced, and as a result, our generative adversarial network can mitigate the convergence problem.
Through the experiments on real images, we validate our proposed method, which can manipulate the generated images as desired by controlling the latent codes of input variables.
In addition, the visual qualities of produced images are effectively maintained, and the model can stably converge to the equilibrium.
However, our model has a difficulty in learning disentangling factors because our model does not regularize the independence between the interpretable factors.
Therefore, in the future, we will develop a generative model that can learn disentangling factors.
American Psychological Association (APA)
Hah, Junghoon& Lee, Woojin& Lee, Jaewook& Park, Saerom. 2018. Information-Based Boundary Equilibrium Generative Adversarial Networks with Interpretable Representation Learning. Computational Intelligence and Neuroscience،Vol. 2018, no. 2018, pp.1-14.
https://search.emarefa.net/detail/BIM-1130807
Modern Language Association (MLA)
Hah, Junghoon…[et al.]. Information-Based Boundary Equilibrium Generative Adversarial Networks with Interpretable Representation Learning. Computational Intelligence and Neuroscience No. 2018 (2018), pp.1-14.
https://search.emarefa.net/detail/BIM-1130807
American Medical Association (AMA)
Hah, Junghoon& Lee, Woojin& Lee, Jaewook& Park, Saerom. Information-Based Boundary Equilibrium Generative Adversarial Networks with Interpretable Representation Learning. Computational Intelligence and Neuroscience. 2018. Vol. 2018, no. 2018, pp.1-14.
https://search.emarefa.net/detail/BIM-1130807
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1130807