# NAM: Non-Adversarial Unsupervised Domain Mapping

arXiv: https://arxiv.org/abs/1806.00804 · HTML: https://mlsanity.com/paper/1806.00804/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2018.

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

- [StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis](https://mlsanity.com/paper/2104.07098/) (2021)
- [Semi-Supervised Image-to-Image Translation using Latent Space Mapping](https://mlsanity.com/paper/2203.15241/) (2022)

## Abstract (arXiv)

Several methods were recently proposed for the task of translating images between domains without prior knowledge in the form of correspondences. The existing methods apply adversarial learning to ensure that the distribution of the mapped source domain is indistinguishable from the target domain, which suffers from known stability issues. In addition, most methods rely heavily on `cycle' relationships between the domains, which enforce a one-to-one mapping. In this work, we introduce an alternative method: Non-Adversarial Mapping (NAM), which separates the task of target domain generative modeling from the cross-domain mapping task. NAM relies on a pre-trained generative model of the target domain, and aligns each source image with an image synthesized from the target domain, while jointly optimizing the domain mapping function. It has several key advantages: higher quality and resolution image translations, simpler and more stable training and reusable target models. Extensive experiments are presented validating the advantages of our method.