# DSDRNet: Disentangling Representation and Reconstruct Network for Domain Generalization

arXiv: https://arxiv.org/abs/2404.13848 · HTML: https://mlsanity.com/paper/2404.13848/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 57 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Builds on (most cited first, 15 of 15)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)
- [DRAW: A Recurrent Neural Network For Image Generation](https://mlsanity.com/paper/1502.04623/) (2015)
- [Learning explanations that are hard to vary](https://mlsanity.com/paper/2009.00329/) (2020)
- [DIVA: Domain Invariant Variational Autoencoders](https://mlsanity.com/paper/1905.10427/) (2019)
- [A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation](https://mlsanity.com/paper/1809.01361/) (2018)

## Abstract (arXiv)

Domain generalization faces challenges due to the distribution shift between training and testing sets, and the presence of unseen target domains. Common solutions include domain alignment, meta-learning, data augmentation, or ensemble learning, all of which rely on domain labels or domain adversarial techniques. In this paper, we propose a Dual-Stream Separation and Reconstruction Network, dubbed DSDRNet. It is a disentanglement-reconstruction approach that integrates features of both inter-instance and intra-instance through dual-stream fusion. The method introduces novel supervised signals by combining inter-instance semantic distance and intra-instance similarity. Incorporating Adaptive Instance Normalization (AdaIN) into a two-stage cyclic reconstruction process enhances self-disentangled reconstruction signals to facilitate model convergence. Extensive experiments on four benchmark datasets demonstrate that DSDRNet outperforms other popular methods in terms of domain generalization capabilities.