# Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate

arXiv: https://arxiv.org/abs/2107.13469 · HTML: https://mlsanity.com/paper/2107.13469/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 68 references that are in the map.
- First posted on arXiv 28 Jul 2021.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (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)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [Generate To Adapt: Aligning Domains using Generative Adversarial Networks](https://mlsanity.com/paper/1704.01705/) (2017)
- [Instance Adaptive Self-Training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2008.12197/) (2020)
- [Domain Adaptation for Structured Output via Discriminative Patch Representations](https://mlsanity.com/paper/1901.05427/) (2019)
- [Transferrable Prototypical Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1904.11227/) (2019)
- [Partial Adversarial Domain Adaptation](https://mlsanity.com/paper/1808.04205/) (2018)
- [Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift](https://mlsanity.com/paper/2003.04475/) (2020)
- [Regularized Learning for Domain Adaptation under Label Shifts](https://mlsanity.com/paper/1903.09734/) (2019)
- [An introduction to domain adaptation and transfer learning](https://mlsanity.com/paper/1812.11806/) (2018)
- [No More Discrimination: Cross City Adaptation of Road Scene Segmenters](https://mlsanity.com/paper/1704.08509/) (2017)
- [Adversarial Dropout Regularization](https://mlsanity.com/paper/1711.01575/) (2017)
- [Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach](https://mlsanity.com/paper/1908.09547/) (2019)
- [DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation](https://mlsanity.com/paper/1804.05827/) (2018)
- [Dual Mixup Regularized Learning for Adversarial Domain Adaptation](https://mlsanity.com/paper/2007.03141/) (2020)
- [Importance Weighted Adversarial Nets for Partial Domain Adaptation](https://mlsanity.com/paper/1803.09210/) (2018)

## Built on by (most cited first, 30 of 43)

- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [RLSbench: Domain Adaptation Under Relaxed Label Shift](https://mlsanity.com/paper/2302.03020/) (2023)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling](https://mlsanity.com/paper/2307.07944/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Pairwise Alignment Improves Graph Domain Adaptation](https://mlsanity.com/paper/2403.01092/) (2024)
- [Any-Shift Prompting for Generalization over Distributions](https://mlsanity.com/paper/2402.10099/) (2024)
- [DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.09988/) (2022)
- [Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts](https://mlsanity.com/paper/2308.08810/) (2023)
- [Prior Knowledge Guided Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.08877/) (2022)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [Memory Consistent Unsupervised Off-the-Shelf Model Adaptation for Source-Relaxed Medical Image Segmentation](https://mlsanity.com/paper/2209.07910/) (2022)
- [Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2211.10412/) (2022)
- [Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2309.12742/) (2023)
- [UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gaps](https://mlsanity.com/paper/2403.17633/) (2024)
- [Partial Domain Adaptation without Domain Alignment](https://mlsanity.com/paper/2108.12867/) (2021)
- [Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation](https://mlsanity.com/paper/2204.05546/) (2022)
- [ALEX: Towards Effective Graph Transfer Learning with Noisy Labels](https://mlsanity.com/paper/2309.14673/) (2023)
- [Self-semantic contour adaptation for cross modality brain tumor segmentation](https://mlsanity.com/paper/2201.05022/) (2022)
- [Unsupervised Domain Adaptation for Segmentation with Black-box Source Model](https://mlsanity.com/paper/2208.07769/) (2022)
- [MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training](https://mlsanity.com/paper/2602.06285/) (2026)
- [Fair Classification via Domain Adaptation: A Dual Adversarial Learning Approach](https://mlsanity.com/paper/2206.03656/) (2022)
- [Photo-realistic Neural Domain Randomization](https://mlsanity.com/paper/2210.12682/) (2022)
- [A Survey of Deep Visual Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2303.09253/) (2023)
- [Structure-aware Unsupervised Tagged-to-Cine MRI Synthesis with Self Disentanglement](https://mlsanity.com/paper/2202.12474/) (2022)
- [Subtype-Aware Dynamic Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.07754/) (2022)
- [Attentive Continuous Generative Self-training for Unsupervised Domain Adaptive Medical Image Translation](https://mlsanity.com/paper/2305.14589/) (2023)
- [Incremental Pseudo-Labeling for Black-Box Unsupervised Domain Adaptation](https://mlsanity.com/paper/2405.16437/) (2024)
- [When Invariant Representation Learning Meets Label Shift: Insufficiency and Theoretical Insights](https://mlsanity.com/paper/2406.16608/) (2024)
- [AVATAR: Adversarial self-superVised domain Adaptation network for TARget domain](https://mlsanity.com/paper/2305.00082/) (2023)

## Abstract (arXiv)

In this work, we propose an adversarial unsupervised domain adaptation (UDA) approach with the inherent conditional and label shifts, in which we aim to align the distributions w.r.t. both p(x|y) and p(y). Since the label is inaccessible in the target domain, the conventional adversarial UDA assumes p(y) is invariant across domains, and relies on aligning p(x) as an alternative to the p(x|y) alignment. To address this, we provide a thorough theoretical and empirical analysis of the conventional adversarial UDA methods under both conditional and label shifts, and propose a novel and practical alternative optimization scheme for adversarial UDA. Specifically, we infer the marginal p(y) and align p(x|y) iteratively in the training, and precisely align the posterior p(y|x) in testing. Our experimental results demonstrate its effectiveness on both classification and segmentation UDA, and partial UDA.