Mode Penalty Generative Adversarial Network with adapted Auto-encoder
This addresses a common issue in GAN training for image generation, though it appears incremental as it builds on existing GAN methods.
The paper tackles the problem of GANs generating only a narrow part of the true distribution or failing to converge by proposing a mode penalty GAN combined with a pre-trained auto-encoder to explicitly represent data in encoded space, resulting in more stable optimization and faster convergence as demonstrated experimentally.
Generative Adversarial Networks (GAN) are trained to generate sample images of interest distribution. To this end, generator network of GAN learns implicit distribution of real data set from the classification with candidate generated samples. Recently, various GANs have suggested novel ideas for stable optimizing of its networks. However, in real implementation, sometimes they still represent a only narrow part of true distribution or fail to converge. We assume this ill posed problem comes from poor gradient from objective function of discriminator, which easily trap the generator in a bad situation. To address this problem, we propose a mode penalty GAN combined with pre-trained auto encoder for explicit representation of generated and real data samples in the encoded space. In this space, we make a generator manifold to follow a real manifold by finding entire modes of target distribution. In addition, penalty for uncovered modes of target distribution is given to the generator which encourages it to find overall target distribution. We demonstrate that applying the proposed method to GANs helps generator's optimization becoming more stable and having faster convergence through experimental evaluations.