# Unsupervised Domain Adaptation via Regularized Conditional Alignment

arXiv: https://arxiv.org/abs/1905.10885 · HTML: https://mlsanity.com/paper/1905.10885/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2019.

## Built on by (most cited first, 30 of 34)

- [Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation](https://mlsanity.com/paper/2205.04183/) (2022)
- [Domain Impression: A Source Data Free Domain Adaptation Method](https://mlsanity.com/paper/2102.09003/) (2021)
- [Semantic Concentration for Domain Adaptation](https://mlsanity.com/paper/2108.05720/) (2021)
- [Specificity-Preserving Federated Learning for MR Image Reconstruction](https://mlsanity.com/paper/2112.05752/) (2021)
- [TeST: Test-time Self-Training under Distribution Shift](https://mlsanity.com/paper/2209.11459/) (2022)
- [Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation](https://mlsanity.com/paper/2109.04015/) (2021)
- [Gradual Domain Adaptation without Indexed Intermediate Domains](https://mlsanity.com/paper/2207.04587/) (2022)
- [Test-Time Adaptation for Depth Completion](https://mlsanity.com/paper/2402.03312/) (2024)
- [Pairwise Alignment Improves Graph Domain Adaptation](https://mlsanity.com/paper/2403.01092/) (2024)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.09988/) (2022)
- [Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions](https://mlsanity.com/paper/2207.10667/) (2022)
- [Multi-Source domain adaptation via supervised contrastive learning and confident consistency regularization](https://mlsanity.com/paper/2106.16093/) (2021)
- [A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation](https://mlsanity.com/paper/2106.11653/) (2021)
- [A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation](https://mlsanity.com/paper/2303.09165/) (2023)
- [Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation](https://mlsanity.com/paper/2407.09367/) (2024)
- [Robust Domain-Free Domain Generalization with Class-aware Alignment](https://mlsanity.com/paper/2102.08897/) (2021)
- [Domain Adaptation with Adversarial Training on Penultimate Activations](https://mlsanity.com/paper/2208.12853/) (2022)
- [Unsupervised Domain Adaptation via Distilled Discriminative Clustering](https://mlsanity.com/paper/2302.11984/) (2023)
- [Progressive Test Time Energy Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2503.16616/) (2025)
- [Adaptive Pseudo-Label Refinement by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.15973/) (2021)
- [Low-confidence Samples Matter for Domain Adaptation](https://mlsanity.com/paper/2202.02802/) (2022)
- [ETA: Energy-based Test-time Adaptation for Depth Completion](https://mlsanity.com/paper/2508.05989/) (2025)
- [Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning](https://mlsanity.com/paper/2103.02808/) (2021)
- [Vicinal and categorical domain adaptation](https://mlsanity.com/paper/2103.03460/) (2021)
- [OneRing: A Simple Method for Source-free Open-partial Domain Adaptation](https://mlsanity.com/paper/2206.03600/) (2022)
- [Relating tSNE and UMAP to Classical Dimensionality Reduction](https://mlsanity.com/paper/2306.11898/) (2023)
- [Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain Adaptation](https://mlsanity.com/paper/2301.13428/) (2023)
- [On the inductive biases of deep domain adaptation](https://mlsanity.com/paper/2109.07920/) (2021)
- [Cycle Label-Consistent Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2205.13957/) (2022)

## Abstract (arXiv)

We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignment ensures that not only the marginal distributions of the domain are aligned, but the labels as well. We propose a novel objective function that encourages the class-conditional distributions to have disjoint support in feature space. We further exploit adversarial regularization to improve the performance of the classifier on the domain for which no annotated data is available.