Escaping from Collapsing Modes in a Constrained Space
This work addresses mode collapse in GANs, a critical issue for researchers and practitioners in generative modeling, though it is incremental as it builds on the existing BEGAN framework.
The paper tackles the problem of mode collapse in Boundary Equilibrium Generative Adversarial Networks (BEGAN) by proposing BEGAN-CS, which incorporates a latent-space constraint to improve training stability and suppress mode collapse without increasing model complexity or degrading image quality.
Generative adversarial networks (GANs) often suffer from unpredictable mode-collapsing during training. We study the issue of mode collapse of Boundary Equilibrium 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 propose a new model, called \emph{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 either increasing the model complexity or degrading the image quality. Further, we visualize the distribution of latent vectors to elucidate the effect of latent-space constraint. 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.