# Domain Translation via Latent Space Mapping

arXiv: https://arxiv.org/abs/2212.03361 · HTML: https://mlsanity.com/paper/2212.03361/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 6 Dec 2022.

## Builds on (most cited first, 24 of 24)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1808.00948/) (2018)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [Simultaneous Deep Transfer Across Domains and Tasks](https://mlsanity.com/paper/1510.02192/) (2015)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation](https://mlsanity.com/paper/1804.05827/) (2018)
- [Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation](https://mlsanity.com/paper/2104.13243/) (2021)
- [AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flows](https://mlsanity.com/paper/1905.12892/) (2019)
- [Beyond Grand Theft Auto V for Training, Testing and Enhancing Deep Learning in Self Driving Cars](https://mlsanity.com/paper/1712.01397/) (2017)
- [DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer](https://mlsanity.com/paper/1908.08074/) (2019)
- [On Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networks](https://mlsanity.com/paper/1807.04015/) (2018)
- [Correlational Neural Networks](https://mlsanity.com/paper/1504.07225/) (2015)
- [GMM-UNIT: Unsupervised Multi-Domain and Multi-Modal Image-to-Image Translation via Attribute Gaussian Mixture Modeling](https://mlsanity.com/paper/2003.06788/) (2020)
- [Domain Adaptation Meets Disentangled Representation Learning and Style Transfer](https://mlsanity.com/paper/1712.09025/) (2017)
- [Deep Neural Networks Regularization for Structured Output Prediction](https://mlsanity.com/paper/1504.07550/) (2015)

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

- [A Unified Framework for Forward and Inverse Problems in Subsurface Imaging using Latent Space Translations](https://mlsanity.com/paper/2410.11247/) (2024)
- [Multiple Noises in Diffusion Model for Semi-Supervised Multi-Domain Translation](https://mlsanity.com/paper/2309.14394/) (2023)

## Abstract (arXiv)

In this paper, we investigate the problem of multi-domain translation: given an element a of domain A, we would like to generate a corresponding b sample in another domain B, and vice versa. Acquiring supervision in multiple domains can be a tedious task, also we propose to learn this translation from one domain to another when supervision is available as a pair (a,b)~ A× B and leveraging possible unpaired data when only a~ A or only b~ B is available. We introduce a new unified framework called Latent Space Mapping (model) that exploits the manifold assumption in order to learn, from each domain, a latent space. Unlike existing approaches, we propose to further regularize each latent space using available domains by learning each dependency between pairs of domains. We evaluate our approach in three tasks performing i) synthetic dataset with image translation, ii) real-world task of semantic segmentation for medical images, and iii) real-world task of facial landmark detection.