# DiDA: Disentangled Synthesis for Domain Adaptation

arXiv: https://arxiv.org/abs/1805.08019 · HTML: https://mlsanity.com/paper/1805.08019/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2018.

## Built on by (most cited first, 10 of 10)

- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.10812/) (2021)
- [Where and What? Examining Interpretable Disentangled Representations](https://mlsanity.com/paper/2104.05622/) (2021)
- [Enhancing Diffusion Models with 3D Perspective Geometry Constraints](https://mlsanity.com/paper/2312.00944/) (2023)
- [Discovering Domain Disentanglement for Generalized Multi-source Domain Adaptation](https://mlsanity.com/paper/2207.05070/) (2022)
- [A Generative Shape Compositional Framework to Synthesise Populations of Virtual Chimaeras](https://mlsanity.com/paper/2210.01607/) (2022)
- [Disentanglement by Cyclic Reconstruction](https://mlsanity.com/paper/2112.12980/) (2021)
- [Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection](https://mlsanity.com/paper/2308.09983/) (2023)
- [A Survey on Adversarial Image Synthesis](https://mlsanity.com/paper/2106.16056/) (2021)
- [ContraFeat: Contrasting Deep Features for Semantic Discovery](https://mlsanity.com/paper/2212.07277/) (2022)

## Abstract (arXiv)

Unsupervised domain adaptation aims at learning a shared model for two related, but not identical, domains by leveraging supervision from a source domain to an unsupervised target domain. A number of effective domain adaptation approaches rely on the ability to extract discriminative, yet domain-invariant, latent factors which are common to both domains. Extracting latent commonality is also useful for disentanglement analysis, enabling separation between the common and the domain-specific features of both domains. In this paper, we present a method for boosting domain adaptation performance by leveraging disentanglement analysis. The key idea is that by learning to separately extract both the common and the domain-specific features, one can synthesize more target domain data with supervision, thereby boosting the domain adaptation performance. Better common feature extraction, in turn, helps further improve the disentanglement analysis and disentangled synthesis. We show that iterating between domain adaptation and disentanglement analysis can consistently improve each other on several unsupervised domain adaptation tasks, for various domain adaptation backbone models.