# CycleGAN with Better Cycles

arXiv: https://arxiv.org/abs/2408.15374 · HTML: https://mlsanity.com/paper/2408.15374/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 3 references that are in the map.
- First posted on arXiv 27 Aug 2024.

## Builds on (most cited first, 3 of 3)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Generating Images with Perceptual Similarity Metrics based on Deep Networks](https://mlsanity.com/paper/1602.02644/) (2016)

## Built on by (most cited first, 2 of 2)

- [DSA-CycleGAN: A Domain Shift Aware CycleGAN for Robust Multi-Stain Glomeruli Segmentation](https://mlsanity.com/paper/2604.18368/) (2026)
- [WarpI2I: Image Warping for Image-to-Image Translation](https://mlsanity.com/paper/2606.31018/) (2026)

## Abstract (arXiv)

CycleGAN provides a framework to train image-to-image translation with unpaired datasets using cycle consistency loss [4]. While results are great in many applications, the pixel level cycle consistency can potentially be problematic and causes unrealistic images in certain cases. In this project, we propose three simple modifications to cycle consistency, and show that such an approach achieves better results with fewer artifacts.