Inverting The Generator Of A Generative Adversarial Network (II)
This provides a method for evaluating and comparing GAN models, which is useful for researchers in generative modeling, though it is incremental as it builds on existing GAN frameworks.
The paper tackles the problem of GANs lacking an inverse mapping from data to latent space by introducing an inversion technique to project images into the latent space of a pre-trained GAN, enabling quantitative comparison of GAN performance based on reconstruction loss across three image datasets.
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.