# Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective

arXiv: https://arxiv.org/abs/2303.13434 · HTML: https://mlsanity.com/paper/2303.13434/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 74 references that are in the map.
- First posted on arXiv 23 Mar 2023.

## Builds on (most cited first, 30 of 53)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Optimal Transport for Domain Adaptation](https://mlsanity.com/paper/1507.00504/) (2015)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [Joint Distribution Optimal Transportation for Domain Adaptation](https://mlsanity.com/paper/1705.08848/) (2017)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning](https://mlsanity.com/paper/1702.08811/) (2017)
- [SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization](https://mlsanity.com/paper/2006.01791/) (2020)
- [Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations](https://mlsanity.com/paper/2003.12237/) (2020)
- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2011.09230/) (2020)

## Built on by (most cited first, 30 of 54)

- [GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation](https://mlsanity.com/paper/2403.16370/) (2024)
- [HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts](https://mlsanity.com/paper/2408.04591/) (2024)
- [PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation](https://mlsanity.com/paper/2406.13378/) (2024)
- [ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts](https://mlsanity.com/paper/2406.10973/) (2024)
- [Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2403.06946/) (2024)
- [Unsupervised Domain Adaption Harnessing Vision-Language Pre-training](https://mlsanity.com/paper/2408.02192/) (2024)
- [Vision transformers in domain adaptation and domain generalization: a study of robustness](https://mlsanity.com/paper/2404.04452/) (2024)
- [GoodSAM++: Bridging Domain and Capacity Gaps via Segment Anything Model for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2408.09115/) (2024)
- [Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal Noises](https://mlsanity.com/paper/2503.02616/) (2025)
- [Agile Multi-Source-Free Domain Adaptation](https://mlsanity.com/paper/2403.05062/) (2024)
- [On f-Divergence Principled Domain Adaptation: An Improved Framework](https://mlsanity.com/paper/2402.01887/) (2024)
- [AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler](https://mlsanity.com/paper/2407.10784/) (2024)
- [UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework](https://mlsanity.com/paper/2409.15264/) (2024)
- [Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Framework](https://mlsanity.com/paper/2411.12558/) (2024)
- [DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception](https://mlsanity.com/paper/2401.08687/) (2024)
- [Enhancing Cross-Modal Fine-Tuning with Gradually Intermediate Modality Generation](https://mlsanity.com/paper/2406.09003/) (2024)
- [CLIP the Divergence: Language-guided Unsupervised Domain Adaptation](https://mlsanity.com/paper/2407.01842/) (2024)
- [Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2411.07794/) (2024)
- [Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance](https://mlsanity.com/paper/2312.04066/) (2023)
- [Source-Free Cross-Modal Knowledge Transfer by Unleashing the Potential of Task-Irrelevant Data](https://mlsanity.com/paper/2401.05014/) (2024)
- [Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videos](https://mlsanity.com/paper/2403.05535/) (2024)
- [Mixup Domain Adaptations for Dynamic Remaining Useful Life Predictions](https://mlsanity.com/paper/2404.04824/) (2024)
- [Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data](https://mlsanity.com/paper/2405.13779/) (2024)
- [SIDA: Synthetic Image Driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2507.18632/) (2025)
- [Unified modality separation: A vision-language framework for unsupervised domain adaptation](https://mlsanity.com/paper/2508.04987/) (2025)
- [Uncertainty-Guided Alignment for Unsupervised Domain Adaptation in Regression](https://mlsanity.com/paper/2401.13721/) (2024)
- [SETA: Semantic-Aware Token Augmentation for Domain Generalization](https://mlsanity.com/paper/2403.11792/) (2024)
- [Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm](https://mlsanity.com/paper/2511.11009/) (2025)
- [A Unified Framework for Unsupervised Domain Adaptation based on Instance Weighting](https://mlsanity.com/paper/2312.05024/) (2023)
- [VLLaVO: Mitigating Visual Gap through LLMs](https://mlsanity.com/paper/2401.03253/) (2024)

## Abstract (arXiv)

Endeavors have been recently made to leverage the vision transformer (ViT) for the challenging unsupervised domain adaptation (UDA) task. They typically adopt the cross-attention in ViT for direct domain alignment. However, as the performance of cross-attention highly relies on the quality of pseudo labels for targeted samples, it becomes less effective when the domain gap becomes large. We solve this problem from a game theory's perspective with the proposed model dubbed as PMTrans, which bridges source and target domains with an intermediate domain. Specifically, we propose a novel ViT-based module called PatchMix that effectively builds up the intermediate domain, i.e., probability distribution, by learning to sample patches from both domains based on the game-theoretical models. This way, it learns to mix the patches from the source and target domains to maximize the cross entropy (CE), while exploiting two semi-supervised mixup losses in the feature and label spaces to minimize it. As such, we interpret the process of UDA as a min-max CE game with three players, including the feature extractor, classifier, and PatchMix, to find the Nash Equilibria. Moreover, we leverage attention maps from ViT to re-weight the label of each patch by its importance, making it possible to obtain more domain-discriminative feature representations. We conduct extensive experiments on four benchmark datasets, and the results show that PMTrans significantly surpasses the ViT-based and CNN-based SoTA methods by +3.6% on Office-Home, +1.4% on Office-31, and +17.7% on DomainNet, respectively.