# CA-UDA: Class-Aware Unsupervised Domain Adaptation with Optimal Assignment and Pseudo-Label Refinement

arXiv: https://arxiv.org/abs/2205.13579 · HTML: https://mlsanity.com/paper/2205.13579/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 26 May 2022.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [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)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks](https://mlsanity.com/paper/1612.05424/) (2016)
- [Label Propagation for Deep Semi-supervised Learning](https://mlsanity.com/paper/1904.04717/) (2019)
- [Simultaneous Deep Transfer Across Domains and Tasks](https://mlsanity.com/paper/1510.02192/) (2015)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [Progressive Feature Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1811.08585/) (2018)
- [Asymmetric Tri-training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1702.08400/) (2017)
- [Transferrable Prototypical Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1904.11227/) (2019)
- [Cluster Alignment with a Teacher for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.09980/) (2019)
- [Unsupervised Domain Adaptation with Similarity Learning](https://mlsanity.com/paper/1711.08995/) (2017)
- [Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2006.04996/) (2020)
- [Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2007.07695/) (2020)

## Built on by (most cited first, 2 of 2)

- [Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation](https://mlsanity.com/paper/2212.02739/) (2022)
- [Towards Cross-Domain Continual Learning](https://mlsanity.com/paper/2402.12490/) (2024)

## Abstract (arXiv)

Recent works on unsupervised domain adaptation (UDA) focus on the selection of good pseudo-labels as surrogates for the missing labels in the target data. However, source domain bias that deteriorates the pseudo-labels can still exist since the shared network of the source and target domains are typically used for the pseudo-label selections. The suboptimal feature space source-to-target domain alignment can also result in unsatisfactory performance. In this paper, we propose CA-UDA to improve the quality of the pseudo-labels and UDA results with optimal assignment, a pseudo-label refinement strategy and class-aware domain alignment. We use an auxiliary network to mitigate the source domain bias for pseudo-label refinement. Our intuition is that the underlying semantics in the target domain can be fully exploited to help refine the pseudo-labels that are inferred from the source features under domain shift. Furthermore, our optimal assignment can optimally align features in the source-to-target domains and our class-aware domain alignment can simultaneously close the domain gap while preserving the classification decision boundaries. Extensive experiments on several benchmark datasets show that our method can achieve state-of-the-art performance in the image classification task.