Inverting the Generator of a Generative Adversarial Network

Generative adversarial networks (GANs) learn a deep generative model that is able to synthesize novel, high-dimensional data samples. New data samples are synthesized by passing latent samples, drawn from a chosen prior distribution, through the generative model. Once trained, the latent space exhib...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2019-07, Vol.30 (7), p.1967-1974
Main Authors: Creswell, Antonia, Bharath, Anil Anthony
Format: Article
Language:English
Subjects:
Backpropagation
Data models
Datasets
Energy management
feature extraction
Gallium nitride
Generative adversarial networks
Generators
image generation
Image reconstruction
Inversion
Learning systems
Mapping
multilayer neural network
pattern recognition
Synthesis
Training
unsupervised learning
Websites
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Generative adversarial networks (GANs) learn a deep generative model that is able to synthesize novel, high-dimensional data samples. New data samples are synthesized 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 downstream 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 pretrained GAN. Using our proposed inversion technique, we are able to identify which attributes of a data set 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 the performance of various GAN models trained on three image data sets. We provide codes for all of our experiments in the website ( https://github.com/ToniCreswell/InvertingGAN ).
ISSN:2162-237X
2162-2388
DOI:10.1109/TNNLS.2018.2875194