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

arXiv: https://arxiv.org/abs/2210.06257 · HTML: https://mlsanity.com/paper/2210.06257/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 12 Oct 2022.

## Builds on (most cited first, 15 of 15)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation](https://mlsanity.com/paper/2001.06535/) (2020)
- [Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis](https://mlsanity.com/paper/1908.06912/) (2019)
- [Distribution Matching Losses Can Hallucinate Features in Medical Image Translation](https://mlsanity.com/paper/1805.08841/) (2018)
- [Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network](https://mlsanity.com/paper/1802.09655/) (2018)
- [Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation](https://mlsanity.com/paper/1907.13590/) (2019)
- [Multi-Domain Image Completion for Random Missing Input Data](https://mlsanity.com/paper/2007.05534/) (2020)
- [Uncertainty-Guided Progressive GANs for Medical Image Translation](https://mlsanity.com/paper/2106.15542/) (2021)
- [Robustness via Uncertainty-aware Cycle Consistency](https://mlsanity.com/paper/2110.12467/) (2021)
- [Multi-Modality Generative Adversarial Networks with Tumor Consistency Loss for Brain MR Image Synthesis](https://mlsanity.com/paper/2005.00925/) (2020)
- [TarGAN: Target-Aware Generative Adversarial Networks for Multi-modality Medical Image Translation](https://mlsanity.com/paper/2105.08993/) (2021)
- [METGAN: Generative Tumour Inpainting and Modality Synthesis in Light Sheet Microscopy](https://mlsanity.com/paper/2104.10993/) (2021)

## Built on by (most cited first, 1 of 1)

- [Brain MR Image Synthesis with 3D Multi-Contrast Self-Attention GAN](https://mlsanity.com/paper/2604.00070/) (2026)

## Abstract (arXiv)

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.