Interpreting Spatially Infinite Generative Models

Abstract

Traditional deep generative models of images and other spatial modalities can only generate fixed sized outputs. The generated images have exactly the same resolution as the training images, which is dictated by the number of layers in the underlying neural network. Recent work has shown, however, that feeding spatial noise vectors into a fully convolutional neural network enables both generation of arbitrary resolution output images as well as training on arbitrary resolution training images. While this work has provided impressive empirical results, little theoretical interpretation was provided to explain the underlying generative process. In this paper we provide a firm theoretical interpretation for infinite spatial generation, by drawing connections to spatial stochastic processes. We use the resulting intuition to improve upon existing spatially infinite generative models to enable more efficient training through a model that we call an infinite generative adversarial network, or $\infty$-GAN. Experiments on world map generation, panoramic images and texture synthesis verify the ability of $\infty$-GAN to efficiently generate images of arbitrary size.

ICML 2020 workshop on Human Interpretability in Machine Learning (WHI 2020)

References in corpus (11)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Machine learning methods for histopathological image analysis
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
• Texture Synthesis with Spatial Generative Adversarial Networks
• Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling
• A step towards procedural terrain generation with GANs