What can we learn about a generated image corrupting its latent representation?

TL;DR

This paper investigates how corrupting the latent space of GANs affects generated image quality, enabling prediction of uncertain regions and reliability assessment in medical image synthesis.

Contribution

It introduces a method to predict image quality and reliability by analyzing the robustness of GANs' latent representations through noise corruption.

Findings

Latent corruption correlates with image uncertainty.

Method predicts unreliable regions in generated images.

Identifies samples unsuitable for downstream tasks.

Abstract

Generative adversarial networks (GANs) offer an effective solution to the image-to-image translation problem, thereby allowing for new possibilities in medical imaging. They can translate images from one imaging modality to another at a low cost. For unpaired datasets, they rely mostly on cycle loss. Despite its effectiveness in learning the underlying data distribution, it can lead to a discrepancy between input and output data. The purpose of this work is to investigate the hypothesis that we can predict image quality based on its latent representation in the GANs bottleneck. We achieve this by corrupting the latent representation with noise and generating multiple outputs. The degree of differences between them is interpreted as the strength of the representation: the more robust the latent representation, the fewer changes in the output image the corruption causes. Our results demonstrate that our proposed method has the ability to i) predict uncertain parts of synthesized images, and ii) identify samples that may not be reliable for downstream tasks, e.g., liver segmentation task.