# Virtual Mixup Training for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/1905.04215 · HTML: https://mlsanity.com/paper/1905.04215/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2019.

## Built on by (most cited first, 21 of 21)

- [Context-Aware Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.03557/) (2021)
- [Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing](https://mlsanity.com/paper/2110.15128/) (2021)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [TeST: Test-time Self-Training under Distribution Shift](https://mlsanity.com/paper/2209.11459/) (2022)
- [ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing](https://mlsanity.com/paper/2210.11539/) (2022)
- [Survey: Image Mixing and Deleting for Data Augmentation](https://mlsanity.com/paper/2106.07085/) (2021)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection](https://mlsanity.com/paper/2106.05499/) (2021)
- [MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation](https://mlsanity.com/paper/2312.07871/) (2023)
- [Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization](https://mlsanity.com/paper/2106.04923/) (2021)
- [Low-confidence Samples Matter for Domain Adaptation](https://mlsanity.com/paper/2202.02802/) (2022)
- [Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup](https://mlsanity.com/paper/2109.07177/) (2021)
- [Cross-lingual Adaptation for Recipe Retrieval with Mixup](https://mlsanity.com/paper/2205.03891/) (2022)
- [Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation](https://mlsanity.com/paper/2206.11180/) (2022)
- [Extending Temporal Data Augmentation for Video Action Recognition](https://mlsanity.com/paper/2211.04888/) (2022)
- [Towards Dynamic and Small Objects Refinement for Unsupervised Domain Adaptative Nighttime Semantic Segmentation](https://mlsanity.com/paper/2310.04747/) (2023)
- [Shuffle Augmentation of Features from Unlabeled Data for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2201.11963/) (2022)
- [LH-Mix: Local Hierarchy Correlation Guided Mixup over Hierarchical Prompt Tuning](https://mlsanity.com/paper/2412.16963/) (2024)
- [Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint](https://mlsanity.com/paper/2105.12939/) (2021)
- [Overcoming the Domain Gap in Neural Action Representations](https://mlsanity.com/paper/2112.01176/) (2021)
- [Multi-modal Domain Adaptation for REG via Relation Transfer](https://mlsanity.com/paper/2309.13247/) (2023)

## Abstract (arXiv)

We study the problem of unsupervised domain adaptation which aims to adapt models trained on a labeled source domain to a completely unlabeled target domain. Recently, the cluster assumption has been applied to unsupervised domain adaptation and achieved strong performance. One critical factor in successful training of the cluster assumption is to impose the locally-Lipschitz constraint to the model. Existing methods only impose the locally-Lipschitz constraint around the training points while miss the other areas, such as the points in-between training data. In this paper, we address this issue by encouraging the model to behave linearly in-between training points. We propose a new regularization method called Virtual Mixup Training (VMT), which is able to incorporate the locally-Lipschitz constraint to the areas in-between training data. Unlike the traditional mixup model, our method constructs the combination samples without using the label information, allowing it to apply to unsupervised domain adaptation. The proposed method is generic and can be combined with most existing models such as the recent state-of-the-art model called VADA. Extensive experiments demonstrate that VMT significantly improves the performance of VADA on six domain adaptation benchmark datasets. For the challenging task of adapting MNIST to SVHN, VMT can improve the accuracy of VADA by over 30%. Code is available at urlhttps://github.com/xudonmao/VMT.