BEGAN v3: Avoiding Mode Collapse in GANs Using Variational Inference
Autor: | Jun-Ho Huh, Jong-Chan Kim, Sung-Wook Park |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
Computer Networks and Communications
Computer science Inference Boundary (topology) lcsh:TK7800-8360 boundary equilibrium generative adversarial networks 02 engineering and technology Field (computer science) computer vision 0202 electrical engineering electronic engineering information engineering Electrical and Electronic Engineering mode collapse Artificial neural network business.industry Deep learning lcsh:Electronics deep learning 020206 networking & telecommunications artificial intelligence Autoencoder Generative model Hardware and Architecture Control and Systems Engineering Signal Processing 020201 artificial intelligence & image processing Artificial intelligence generative adversarial networks business Generator (mathematics) variational inference |
Zdroj: | Electronics, Vol 9, Iss 688, p 688 (2020) Electronics Volume 9 Issue 4 |
ISSN: | 2079-9292 |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |