Escaping from Collapsing Modes in a Constrained Space

• Main Authors: Chang, Chia-Che, 張嘉哲
• Other Authors: Lee, Che-Rung
• Format: Others
• Language: en_US
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/kjdve5

碩士 === 國立清華大學 === 資訊工程學系所 === 106 === Generative adversarial networks (GANs) often suffer from unpredictable mode- collapsing during training. We study the issue of mode collapse of Boundary Equilib- rium Generative Adversarial Network (BEGAN), which is one of the state-of-the-art generative models. Despite its potential of generating high-quality images, we find that BEGAN tends to collapse at some modes after a period of training. We pro- pose a new model, called BEGAN with a Constrained Space (BEGAN-CS), which includes a latent-space constraint in the loss function. We show that BEGAN-CS can significantly improve training stability and suppress mode collapse without ei- ther increasing the model complexity or degrading the image quality. Further, we visualize the distribution of latent vectors to elucidate the effect of latent-space con- straint. The experimental results show that our method has additional advantages of being able to train on small datasets and to generate images similar to a given real image yet with variations of designated attributes on-the-fly.