# Exploiting Both Domain-specific and Invariant Knowledge via a Win-win Transformer for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2111.12941 · HTML: https://mlsanity.com/paper/2111.12941/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 64 references that are in the map.
- First posted on arXiv 25 Nov 2021.

## Builds on (most cited first, 30 of 51)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [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)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [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)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Domain-Specific Batch Normalization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1906.03950/) (2019)

## Built on by (most cited first, 7 of 7)

- [Vision transformers in domain adaptation and domain generalization: a study of robustness](https://mlsanity.com/paper/2404.04452/) (2024)
- [Towards Unsupervised Domain Adaptation via Domain-Transformer](https://mlsanity.com/paper/2202.13777/) (2022)
- [Efficient unsupervised domain adaptation via self-supervised vision transformer and synergistic cross-domain alignment](https://mlsanity.com/paper/2407.21311/) (2024)
- [Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation](https://mlsanity.com/paper/2212.02739/) (2022)
- [TransAdapter: Vision Transformer for Feature-Centric Unsupervised Domain Adaptation](https://mlsanity.com/paper/2412.04073/) (2024)
- [Unsupervised Domain Adaptation via Style-Aware Self-intermediate Domain](https://mlsanity.com/paper/2209.01870/) (2022)
- [Pick up the PACE: Fast and Simple Domain Adaptation via Ensemble Pseudo-Labeling](https://mlsanity.com/paper/2205.13508/) (2022)

## Abstract (arXiv)

Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Most existing UDA approaches enable knowledge transfer via learning domain-invariant representation and sharing one classifier across two domains. However, ignoring the domain-specific information that are related to the task, and forcing a unified classifier to fit both domains will limit the feature expressiveness in each domain. In this paper, by observing that the Transformer architecture with comparable parameters can generate more transferable representations than CNN counterparts, we propose a Win-Win TRansformer framework (WinTR) that separately explores the domain-specific knowledge for each domain and meanwhile interchanges cross-domain knowledge. Specifically, we learn two different mappings using two individual classification tokens in the Transformer, and design for each one a domain-specific classifier. The cross-domain knowledge is transferred via source guided label refinement and single-sided feature alignment with respect to source or target, which keeps the integrity of domain-specific information. Extensive experiments on three benchmark datasets show that our method outperforms the state-of-the-art UDA methods, validating the effectiveness of exploiting both domain-specific and invariant