BourGAN: Generative Networks with Metric Embeddings

Abstract

This paper addresses the mode collapse for generative adversarial networks (GANs). We view modes as a geometric structure of data distribution in a metric space. Under this geometric lens, we embed subsamples of the dataset from an arbitrary metric space into the l2 space, while preserving their pairwise distance distribution. Not only does this metric embedding determine the dimensionality of the latent space automatically, it also enables us to construct a mixture of Gaussians to draw latent space random vectors. We use the Gaussian mixture model in tandem with a simple augmentation of the objective function to train GANs. Every major step of our method is supported by theoretical analysis, and our experiments on real and synthetic data confirm that the generator is able to produce samples spreading over most of the modes while avoiding unwanted samples, outperforming several recent GAN variants on a number of metrics and offering new features.

arXiv commentNeural Information Processing Systems, 2018

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Generative Adversarial Text to Image Synthesis
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Energy-based Generative Adversarial Network
• Adversarial Feature Learning
• Adversarially Learned Inference
• Autoencoding beyond pixels using a learned similarity metric
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• A note on the evaluation of generative models
• Mode Regularized Generative Adversarial Networks
• Optimizing the Latent Space of Generative Networks
• AdaGAN: Boosting Generative Models
• Gradient descent GAN optimization is locally stable
• Learning Wasserstein Embeddings

Cited by in corpus (7)

• Manifold embedding data-driven mechanics
• RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification
• GDPP: Learning Diverse Generations Using Determinantal Point Process
• Self-Supervised GANs with Label Augmentation
• Unsupervised multi-modal Styled Content Generation
• Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution
• Normalized Diversification