# Domain Separation Networks

arXiv: https://arxiv.org/abs/1608.06019 · HTML: https://mlsanity.com/paper/1608.06019/

## Key facts

- Cited by 320 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2016.

## Built on by (most cited first, 30 of 320)

- [Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models](https://mlsanity.com/paper/1911.03393/) (2019)
- [Learning to Diversify for Single Domain Generalization](https://mlsanity.com/paper/2108.11726/) (2021)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Progressive Domain Expansion Network for Single Domain Generalization](https://mlsanity.com/paper/2103.16050/) (2021)
- [Invariant Information Bottleneck for Domain Generalization](https://mlsanity.com/paper/2106.06333/) (2021)
- [Modular Deep Learning](https://mlsanity.com/paper/2302.11529/) (2023)
- [On Inductive Biases for Heterogeneous Treatment Effect Estimation](https://mlsanity.com/paper/2106.03765/) (2021)
- [Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization](https://mlsanity.com/paper/2202.06856/) (2022)
- [Domain Adaptation for Time Series Forecasting via Attention Sharing](https://mlsanity.com/paper/2102.06828/) (2021)
- [Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks](https://mlsanity.com/paper/2110.08398/) (2021)
- [Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2303.03770/) (2023)
- [Multi-Source Domain Adaptation with Mixture of Experts](https://mlsanity.com/paper/1809.02256/) (2018)
- [Transferability in Deep Learning: A Survey](https://mlsanity.com/paper/2201.05867/) (2022)
- [Dynamic Weighted Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.13814/) (2021)
- [Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning](https://mlsanity.com/paper/2303.05952/) (2023)
- [CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2107.00085/) (2021)
- [Prompt Vision Transformer for Domain Generalization](https://mlsanity.com/paper/2208.08914/) (2022)
- [Diverse Adversaries for Mitigating Bias in Training](https://mlsanity.com/paper/2101.10001/) (2021)
- [Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data](https://mlsanity.com/paper/2107.11978/) (2021)
- [Uncertainty-guided Source-free Domain Adaptation](https://mlsanity.com/paper/2208.07591/) (2022)
- [Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation](https://mlsanity.com/paper/2108.07628/) (2021)
- [Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density](https://mlsanity.com/paper/2108.10860/) (2021)
- [Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions](https://mlsanity.com/paper/2111.08446/) (2021)
- [Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval](https://mlsanity.com/paper/2209.11572/) (2022)
- [Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentation](https://mlsanity.com/paper/2101.06853/) (2021)
- [BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation](https://mlsanity.com/paper/2204.02811/) (2022)
- [Transporting Causal Mechanisms for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.11055/) (2021)
- [No-Reference Point Cloud Quality Assessment via Domain Adaptation](https://mlsanity.com/paper/2112.02851/) (2021)
- [Multimodal Variational Auto-encoder based Audio-Visual Segmentation](https://mlsanity.com/paper/2310.08303/) (2023)
- [SwitchTab: Switched Autoencoders Are Effective Tabular Learners](https://mlsanity.com/paper/2401.02013/) (2024)

## Abstract (arXiv)

The cost of large scale data collection and annotation often makes the application of machine learning algorithms to new tasks or datasets prohibitively expensive. One approach circumventing this cost is training models on synthetic data where annotations are provided automatically. Despite their appeal, such models often fail to generalize from synthetic to real images, necessitating domain adaptation algorithms to manipulate these models before they can be successfully applied. Existing approaches focus either on mapping representations from one domain to the other, or on learning to extract features that are invariant to the domain from which they were extracted. However, by focusing only on creating a mapping or shared representation between the two domains, they ignore the individual characteristics of each domain. We suggest that explicitly modeling what is unique to each domain can improve a model's ability to extract domain-invariant features. Inspired by work on private-shared component analysis, we explicitly learn to extract image representations that are partitioned into two subspaces: one component which is private to each domain and one which is shared across domains. Our model is trained not only to perform the task we care about in the source domain, but also to use the partitioned representation to reconstruct the images from both domains. Our novel architecture results in a model that outperforms the state-of-the-art on a range of unsupervised domain adaptation scenarios and additionally produces visualizations of the private and shared representations enabling interpretation of the domain adaptation process.