# TriGAN: Image-to-Image Translation for Multi-Source Domain Adaptation

arXiv: https://arxiv.org/abs/2004.08769 · HTML: https://mlsanity.com/paper/2004.08769/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation](https://mlsanity.com/paper/2104.00808/) (2021)
- [Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2306.09098/) (2023)
- [Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation](https://mlsanity.com/paper/2302.01516/) (2023)
- [Masked Discriminators for Content-Consistent Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2309.13188/) (2023)
- [Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation](https://mlsanity.com/paper/2409.16706/) (2024)
- [Event USKT : U-State Space Model in Knowledge Transfer for Event Cameras](https://mlsanity.com/paper/2411.15276/) (2024)
- [Separating Content and Style for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2110.14404/) (2021)

## Abstract (arXiv)

Most domain adaptation methods consider the problem of transferring knowledge to the target domain from a single source dataset. However, in practical applications, we typically have access to multiple sources. In this paper we propose the first approach for Multi-Source Domain Adaptation (MSDA) based on Generative Adversarial Networks. Our method is inspired by the observation that the appearance of a given image depends on three factors: the domain, the style (characterized in terms of low-level features variations) and the content. For this reason we propose to project the image features onto a space where only the dependence from the content is kept, and then re-project this invariant representation onto the pixel space using the target domain and style. In this way, new labeled images can be generated which are used to train a final target classifier. We test our approach using common MSDA benchmarks, showing that it outperforms state-of-the-art methods.