Inverting The Generator Of A Generative Adversarial Network (II)

Abstract

Generative adversarial networks (GANs) learn a deep generative model that is able to synthesise novel, high-dimensional data samples. New data samples are synthesised by passing latent samples, drawn from a chosen prior distribution, through the generative model. Once trained, the latent space exhibits interesting properties, that may be useful for down stream tasks such as classification or retrieval. Unfortunately, GANs do not offer an "inverse model", a mapping from data space back to latent space, making it difficult to infer a latent representation for a given data sample. In this paper, we introduce a technique, inversion, to project data samples, specifically images, to the latent space using a pre-trained GAN. Using our proposed inversion technique, we are able to identify which attributes of a dataset a trained GAN is able to model and quantify GAN performance, based on a reconstruction loss. We demonstrate how our proposed inversion technique may be used to quantitatively compare performance of various GAN models trained on three image datasets. We provide code for all of our experiments, https://github.com/ToniCreswell/InvertingGAN.

arXiv commentUnder review at IEEE TNNLS

References in corpus (8)

• Improved Techniques for Training GANs
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• Adversarial Feature Learning
• Adversarially Learned Inference
• Towards Principled Methods for Training Generative Adversarial Networks
• Generative Visual Manipulation on the Natural Image Manifold
• Task Specific Adversarial Cost Function
• Learning Inverse Mapping by Autoencoder based Generative Adversarial Nets

Cited by in corpus (11)

• Generative Adversarial Networks: An Overview
• Optimizing the Latent Space of Generative Networks
• Precise Recovery of Latent Vectors from Generative Adversarial Networks
• Controlling generative models with continuous factors of variations
• Gradient-based deterministic inversion of geophysical data with Generative Adversarial Networks: is it feasible?
• MeshGAN: Non-linear 3D Morphable Models of Faces
• Correction by Projection: Denoising Images with Generative Adversarial Networks
• Learning Inverse Mapping by Autoencoder based Generative Adversarial Nets
• Towards Recovery of Conditional Vectors from Conditional Generative Adversarial Networks
• Generative Visual Rationales
• Generalized Latent Variable Recovery for Generative Adversarial Networks