# Dual-stream Feature Augmentation for Domain Generalization

arXiv: https://arxiv.org/abs/2409.04699 · HTML: https://mlsanity.com/paper/2409.04699/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 7 Sep 2024.

## Builds on (most cited first, 10 of 10)

- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [Deep Domain-Adversarial Image Generation for Domain Generalisation](https://mlsanity.com/paper/2003.06054/) (2020)
- [Exploiting Domain-Specific Features to Enhance Domain Generalization](https://mlsanity.com/paper/2110.09410/) (2021)
- [Deconfounded Video Moment Retrieval with Causal Intervention](https://mlsanity.com/paper/2106.01534/) (2021)
- [Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval](https://mlsanity.com/paper/2007.02503/) (2020)
- [Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization](https://mlsanity.com/paper/2108.08596/) (2021)
- [Domain Generalization via Frequency-domain-based Feature Disentanglement and Interaction](https://mlsanity.com/paper/2201.08029/) (2022)
- [BP-Triplet Net for Unsupervised Domain Adaptation: A Bayesian Perspective](https://mlsanity.com/paper/2202.09541/) (2022)
- [Enhancing Person Re-identification in a Self-trained Subspace](https://mlsanity.com/paper/1704.06020/) (2017)

## Built on by (most cited first, 1 of 1)

- [Closing the Confusion Loop: CLIP-Guided Alignment for Source-Free Domain Adaptation](https://mlsanity.com/paper/2602.08730/) (2026)

## Abstract (arXiv)

Domain generalization (DG) task aims to learn a robust model from source domains that could handle the out-of-distribution (OOD) issue. In order to improve the generalization ability of the model in unseen domains, increasing the diversity of training samples is an effective solution. However, existing augmentation approaches always have some limitations. On the one hand, the augmentation manner in most DG methods is not enough as the model may not see the perturbed features in approximate the worst case due to the randomness, thus the transferability in features could not be fully explored. On the other hand, the causality in discriminative features is not involved in these methods, which harms the generalization ability of model due to the spurious correlations. To address these issues, we propose a Dual-stream Feature Augmentation~(DFA) method by constructing some hard features from two perspectives. Firstly, to improve the transferability, we construct some targeted features with domain related augmentation manner. Through the guidance of uncertainty, some hard cross-domain fictitious features are generated to simulate domain shift. Secondly, to take the causality into consideration, the spurious correlated non-causal information is disentangled by an adversarial mask, then the more discriminative features can be extracted through these hard causal related information. Different from previous fixed synthesizing strategy, the two augmentations are integrated into a unified learnable feature disentangle model. Based on these hard features, contrastive learning is employed to keep the semantic consistency and improve the robustness of the model. Extensive experiments on several datasets demonstrated that our approach could achieve state-of-the-art performance for domain generalization. Our code is available at: https://github.com/alusi123/DFA.