# Show, Attend and Translate: Unsupervised Image Translation with Self-Regularization and Attention

arXiv: https://arxiv.org/abs/1806.06195 · HTML: https://mlsanity.com/paper/1806.06195/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2018.

## Built on by (most cited first, 10 of 10)

- [AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation](https://mlsanity.com/paper/2102.12593/) (2021)
- [Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks](https://mlsanity.com/paper/2103.05422/) (2021)
- [FEAT: Face Editing with Attention](https://mlsanity.com/paper/2202.02713/) (2022)
- [Multi-cropping Contrastive Learning and Domain Consistency for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2304.12235/) (2023)
- [Learning Unsupervised Cross-domain Image-to-Image Translation Using a Shared Discriminator](https://mlsanity.com/paper/2102.04699/) (2021)
- [Content Preserving Image Translation with Texture Co-occurrence and Spatial Self-Similarity for Texture Debiasing and Domain Adaptation](https://mlsanity.com/paper/2110.07920/) (2021)
- [Masked Discriminators for Content-Consistent Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2309.13188/) (2023)
- [Diffusion based Zero-shot Medical Image-to-Image Translation for Cross Modality Segmentation](https://mlsanity.com/paper/2404.01102/) (2024)
- [Separating Content and Style for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2110.14404/) (2021)
- [Global and Local Alignment Networks for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2111.10346/) (2021)

## Abstract (arXiv)

Image translation between two domains is a class of problems aiming to learn mapping from an input image in the source domain to an output image in the target domain. It has been applied to numerous domains, such as data augmentation, domain adaptation, and unsupervised training. When paired training data is not accessible, image translation becomes an ill-posed problem. We constrain the problem with the assumption that the translated image needs to be perceptually similar to the original image and also appears to be drawn from the new domain, and propose a simple yet effective image translation model consisting of a single generator trained with a self-regularization term and an adversarial term. We further notice that existing image translation techniques are agnostic to the subjects of interest and often introduce unwanted changes or artifacts to the input. Thus we propose to add an attention module to predict an attention map to guide the image translation process. The module learns to attend to key parts of the image while keeping everything else unaltered, essentially avoiding undesired artifacts or changes. The predicted attention map also opens door to applications such as unsupervised segmentation and saliency detection. Extensive experiments and evaluations show that our model while being simpler, achieves significantly better performance than existing image translation methods.