# Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders

arXiv: https://arxiv.org/abs/1712.02050 · HTML: https://mlsanity.com/paper/1712.02050/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2017.

## Built on by (most cited first, 11 of 11)

- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator](https://mlsanity.com/paper/2205.00146/) (2022)
- [GAN-based Facial Attribute Manipulation](https://mlsanity.com/paper/2210.12683/) (2022)
- [A Unified Hyper-GAN Model for Unpaired Multi-contrast MR Image Translation](https://mlsanity.com/paper/2107.11945/) (2021)
- [An Optimal Transport Approach to Personalized Federated Learning](https://mlsanity.com/paper/2206.02468/) (2022)
- [Physics-informed Guided Disentanglement in Generative Networks](https://mlsanity.com/paper/2107.14229/) (2021)
- [FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks](https://mlsanity.com/paper/2112.00532/) (2021)
- [Factored couplings in multi-marginal optimal transport via difference of convex programming](https://mlsanity.com/paper/2110.00629/) (2021)
- [Unsupervised Multiple Domain Translation through Controlled Disentanglement in Variational Autoencoder](https://mlsanity.com/paper/2401.09180/) (2024)
- [Cross-modal Face- and Voice-style Transfer](https://mlsanity.com/paper/2302.13838/) (2023)
- [A Unified Kantorovich Duality for Multimarginal Optimal Transport](https://mlsanity.com/paper/2601.17171/) (2026)

## Abstract (arXiv)

Unsupervised Image-to-Image Translation achieves spectacularly advanced developments nowadays. However, recent approaches mainly focus on one model with two domains, which may face heavy burdens with large cost of O(n2) training time and model parameters, under such a requirement that n domains are freely transferred to each other in a general setting. To address this problem, we propose a novel and unified framework named Domain-Bank, which consists of a global shared auto-encoder and n domain-specific encoders/decoders, assuming that a universal shared-latent sapce can be projected. Thus, we yield O(n) complexity in model parameters along with a huge reduction of the time budgets. Besides the high efficiency, we show the comparable (or even better) image translation results over state-of-the-arts on various challenging unsupervised image translation tasks, including face image translation, fashion-clothes translation and painting style translation. We also apply the proposed framework to domain adaptation and achieve state-of-the-art performance on digit benchmark datasets. Further, thanks to the explicit representation of the domain-specific decoders as well as the universal shared-latent space, it also enables us to conduct incremental learning to add a new domain encoder/decoder. Linear combination of different domains' representations is also obtained by fusing the corresponding decoders.