# Unsupervised Cross-Domain Image Generation

arXiv: https://arxiv.org/abs/1611.02200 · HTML: https://mlsanity.com/paper/1611.02200/

## Key facts

- Cited by 125 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2016.

## Built on by (most cited first, 30 of 125)

- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [Splicing ViT Features for Semantic Appearance Transfer](https://mlsanity.com/paper/2201.00424/) (2022)
- [Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models](https://mlsanity.com/paper/1911.03393/) (2019)
- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [One-Step Image Translation with Text-to-Image Models](https://mlsanity.com/paper/2403.12036/) (2024)
- [Talk-to-Edit: Fine-Grained Facial Editing via Dialog](https://mlsanity.com/paper/2109.04425/) (2021)
- [Visual Prompt Tuning for Test-time Domain Adaptation](https://mlsanity.com/paper/2210.04831/) (2022)
- [DG-Font: Deformable Generative Networks for Unsupervised Font Generation](https://mlsanity.com/paper/2104.03064/) (2021)
- [Synthetic Data -- what, why and how?](https://mlsanity.com/paper/2205.03257/) (2022)
- [Image-to-image Translation via Hierarchical Style Disentanglement](https://mlsanity.com/paper/2103.01456/) (2021)
- [Disentangled Cycle Consistency for Highly-realistic Virtual Try-On](https://mlsanity.com/paper/2103.09479/) (2021)
- [Transferability in Deep Learning: A Survey](https://mlsanity.com/paper/2201.05867/) (2022)
- [From Shadow Generation to Shadow Removal](https://mlsanity.com/paper/2103.12997/) (2021)
- [A Survey on Deep Domain Adaptation for LiDAR Perception](https://mlsanity.com/paper/2106.02377/) (2021)
- [Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2106.09016/) (2021)
- [Model Adaptation: Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2502.19316/) (2025)
- [An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era](https://mlsanity.com/paper/2210.03538/) (2022)
- [Visualizing Adapted Knowledge in Domain Transfer](https://mlsanity.com/paper/2104.10602/) (2021)
- [Modulated Contrast for Versatile Image Synthesis](https://mlsanity.com/paper/2203.09333/) (2022)
- [Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2104.01286/) (2021)
- [Memory-guided Unsupervised Image-to-image Translation](https://mlsanity.com/paper/2104.05170/) (2021)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames](https://mlsanity.com/paper/2102.12841/) (2021)
- [Domain-Adversarial Training of Self-Attention Based Networks for Land Cover Classification using Multi-temporal Sentinel-2 Satellite Imagery](https://mlsanity.com/paper/2104.00564/) (2021)
- [SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2103.16219/) (2021)
- [PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal](https://mlsanity.com/paper/2105.12324/) (2021)
- [Mutually improved endoscopic image synthesis and landmark detection in unpaired image-to-image translation](https://mlsanity.com/paper/2107.06941/) (2021)
- [Unsupervised Structure-Texture Separation Network for Oracle Character Recognition](https://mlsanity.com/paper/2205.06549/) (2022)
- [Divergence Optimization for Noisy Universal Domain Adaptation](https://mlsanity.com/paper/2104.00246/) (2021)

## Abstract (arXiv)

We study the problem of transferring a sample in one domain to an analog sample in another domain. Given two related domains, S and T, we would like to learn a generative function G that maps an input sample from S to the domain T, such that the output of a given function f, which accepts inputs in either domains, would remain unchanged. Other than the function f, the training data is unsupervised and consist of a set of samples from each domain. The Domain Transfer Network (DTN) we present employs a compound loss function that includes a multiclass GAN loss, an f-constancy component, and a regularizing component that encourages G to map samples from T to themselves. We apply our method to visual domains including digits and face images and demonstrate its ability to generate convincing novel images of previously unseen entities, while preserving their identity.