MMGAN: Generative Adversarial Networks for Multi-Modal Distributions
arXiv:1911.06663
Abstract
Over the past years, Generative Adversarial Networks (GANs) have shown a remarkable generation performance especially in image synthesis. Unfortunately, they are also known for having an unstable training process and might loose parts of the data distribution for heterogeneous input data. In this paper, we propose a novel GAN extension for multi-modal distribution learning (MMGAN). In our approach, we model the latent space as a Gaussian mixture model with a number of clusters referring to the number of disconnected data manifolds in the observation space, and include a clustering network, which relates each data manifold to one Gaussian cluster. Thus, the training gets more stable. Moreover, MMGAN allows for clustering real data according to the learned data manifold in the latent space. By a series of benchmark experiments, we illustrate that MMGAN outperforms competitive state-of-the-art models in terms of clustering performance.
References in corpus (10)
- Scikit-learn: Machine Learning in Python
- Auto-Encoding Variational Bayes
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- The relativistic discriminator: a key element missing from standard GAN
- Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
- Adversarial Autoencoders
- Gradient descent GAN optimization is locally stable
- Disconnected Manifold Learning for Generative Adversarial Networks
- Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Images
- Universality Theorems for Generative Models