# Learning to Transfer: Unsupervised Meta Domain Translation

arXiv: https://arxiv.org/abs/1906.00181 · HTML: https://mlsanity.com/paper/1906.00181/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2019.

## Built on by (most cited first, 4 of 4)

- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023)
- [ManiFest: Manifold Deformation for Few-shot Image Translation](https://mlsanity.com/paper/2111.13681/) (2021)
- [Hierarchical Conditional Semi-Paired Image-to-Image Translation For Multi-Task Image Defect Correction On Shopping Websites](https://mlsanity.com/paper/2309.05883/) (2023)

## Abstract (arXiv)

Unsupervised domain translation has recently achieved impressive performance with Generative Adversarial Network (GAN) and sufficient (unpaired) training data. However, existing domain translation frameworks form in a disposable way where the learning experiences are ignored and the obtained model cannot be adapted to a new coming domain. In this work, we take on unsupervised domain translation problems from a meta-learning perspective. We propose a model called Meta-Translation GAN (MT-GAN) to find good initialization of translation models. In the meta-training procedure, MT-GAN is explicitly trained with a primary translation task and a synthesized dual translation task. A cycle-consistency meta-optimization objective is designed to ensure the generalization ability. We demonstrate effectiveness of our model on ten diverse two-domain translation tasks and multiple face identity translation tasks. We show that our proposed approach significantly outperforms the existing domain translation methods when each domain contains no more than ten training samples.