Abstract
In the field of deep learning, the generative model did not attract much attention until GANs (generative adversarial networks) appeared. In 2014, Google’s Ian Goodfellow proposed a generative model called GANs. GANs use different structures and objective functions from the existing generative model. For example, GANs use two neural networks: a generator that creates a realistic image, and a discriminator that distinguishes whether the input is real or synthetic. If there are no problems in the training process, GANs can generate images that are difficult even for experts to distinguish in terms of authenticity. Currently, GANs are the most researched subject in the field of computer vision, which deals with the technology of image style translation, synthesis, and generation, and various models have been unveiled. The issues raised are also improving one by one. In image synthesis, BEGAN (Boundary Equilibrium Generative Adversarial Network), which outperforms the previously announced GANs, learns the latent space of the image, while balancing the generator and discriminator. Nonetheless, BEGAN also has a mode collapse wherein the generator generates only a few images or a single one. Although BEGAN-CS (Boundary Equilibrium Generative Adversarial Network with Constrained Space), which was improved in terms of loss function, was introduced, it did not solve the mode collapse. The discriminator structure of BEGAN-CS is AE (AutoEncoder), which cannot create a particularly useful or structured latent space. Compression performance is not good either. In this paper, this characteristic of AE is considered to be related to the occurrence of mode collapse. Thus, we used VAE (Variational AutoEncoder), which added statistical techniques to AE. As a result of the experiment, the proposed model did not cause mode collapse but converged to a better state than BEGAN-CS.
Highlights
The term deep learning has become so familiar [1]
BEGAN-CS (Boundary Equilibrium Generative Adversarial Network with Constrained Space), which was improved in terms of loss function, was introduced, it did not solve the mode collapse [7]
Both BEGAN and BEGAN-CS have not solved the mode collapse, but the proposed method is based on boundary equilibrium and constrained space algorithms
Summary
The term deep learning has become so familiar [1]. Deep learning has rapidly expanded its range of use from AlphaGo’s go match, which we all watched with interest, to professional jobs such as doctors and lawyers and to cultural and artistic fields that require creativity. GANs use a structure and an objective function that are different from those of the previously introduced generative model. They use two neural networks called generator and discriminator. BEGAN (boundary equilibrium generative adversarial network), which performed better than the previously introduced GANs in image synthesis, learns the latent space of images while balancing and adjusting the generator and the discriminator [6]. BEGAN-CS (Boundary Equilibrium Generative Adversarial Network with Constrained Space), which was improved in terms of loss function, was introduced, it did not solve the mode collapse [7]. The GANs model with VAE as the discriminator was implemented to verify the performance of mode collapse, training instability, and evaluation criteria. The rest of this paper is organized as follows: Section 1 describes the background, purpose, and content and scope of the research; Section 2 presents the latest research related to the structure and application of GANs; Section 3 discusses the structure of BEGAN-CS, learning algorithms, and problems that arise during training; in Section 4, we compare and describe how the features of the proposed model designed for performance improvement are different from those of the existing models; Section 5 presents our experimentation and evaluation as to whether the performance of the proposed model improved as intended; Section 6 discusses the conclusion and future tasks
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
