# Mask CycleGAN: Unpaired Multi-modal Domain Translation with Interpretable Latent Variable

arXiv: https://arxiv.org/abs/2205.06969 · HTML: https://mlsanity.com/paper/2205.06969/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 14 May 2022.

## Builds on (most cited first, 5 of 5)

- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium](https://mlsanity.com/paper/1706.08500/) (2017)
- [Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data](https://mlsanity.com/paper/1802.10151/) (2018)
- [Unsupervised Attention-guided Image to Image Translation](https://mlsanity.com/paper/1806.02311/) (2018)

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

- [xAI-CycleGAN, a Cycle-Consistent Generative Assistive Network](https://mlsanity.com/paper/2306.15760/) (2023)
- [Enabling 24-hour Agricultural Robotics: Unsupervised Day-to-Night Cross-Modal Image Translation for Nighttime Visual Navigation](https://mlsanity.com/paper/2607.12065/) (2026)

## Abstract (arXiv)

We propose Mask CycleGAN, a novel architecture for unpaired image domain translation built based on CycleGAN, with an aim to address two issues: 1) unimodality in image translation and 2) lack of interpretability of latent variables. Our innovation in the technical approach is comprised of three key components: masking scheme, generator and objective. Experimental results demonstrate that this architecture is capable of bringing variations to generated images in a controllable manner and is reasonably robust to different masks.