# Bayesian Uncertainty Matching for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/1906.09693 · HTML: https://mlsanity.com/paper/1906.09693/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2019.

## Built on by (most cited first, 22 of 22)

- [Domain Impression: A Source Data Free Domain Adaptation Method](https://mlsanity.com/paper/2102.09003/) (2021)
- [Context-Aware Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.03557/) (2021)
- [Uncertainty-guided Source-free Domain Adaptation](https://mlsanity.com/paper/2208.07591/) (2022)
- [Subspace Identification for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2310.04723/) (2023)
- [Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models](https://mlsanity.com/paper/2103.00429/) (2021)
- [Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.13986/) (2022)
- [Bayesian Active Learning for Sim-to-Real Robotic Perception](https://mlsanity.com/paper/2109.11547/) (2021)
- [Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling](https://mlsanity.com/paper/2206.01319/) (2022)
- [Fast and Accurate Importance Weighting for Correcting Sample Bias](https://mlsanity.com/paper/2209.04215/) (2022)
- [Adaptive Pseudo-Label Refinement by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.15973/) (2021)
- [Unsupervised Domain Adaptation for Low-dose CT Reconstruction via Bayesian Uncertainty Alignment](https://mlsanity.com/paper/2302.13251/) (2023)
- [Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection](https://mlsanity.com/paper/2108.12612/) (2021)
- [Uncertainty-Guided Alignment for Unsupervised Domain Adaptation in Regression](https://mlsanity.com/paper/2401.13721/) (2024)
- [Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.00727/) (2021)
- [Joint covariate-alignment and concept-alignment: a framework for domain generalization](https://mlsanity.com/paper/2208.00898/) (2022)
- [Dynamic Proxy Domain Generalizes the Crowd Localization by Better Binary Segmentation](https://mlsanity.com/paper/2404.13992/) (2024)
- [h-calibration: Rethinking Classifier Recalibration with Probabilistic Error-Bounded Objective](https://mlsanity.com/paper/2506.17968/) (2025)
- [Exploring Dropout Discriminator for Domain Adaptation](https://mlsanity.com/paper/2107.04231/) (2021)
- [Time Series Domain Adaptation via Latent Invariant Causal Mechanism](https://mlsanity.com/paper/2502.16637/) (2025)
- [VirDA: Reusing Backbone for Unsupervised Domain Adaptation with Visual Reprogramming](https://mlsanity.com/paper/2510.01660/) (2025)
- [Hierarchical Bayesian Framework for Multisource Domain Adaptation](https://mlsanity.com/paper/2512.18553/) (2025)
- [Evidential Domain Adaptation for Remaining Useful Life Prediction with Incomplete Degradation](https://mlsanity.com/paper/2603.15687/) (2026)

## Abstract (arXiv)

Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reducing domain shift by matching marginal feature distributions through deep transformations on the input features, due to the unavailability of target domain labels. We show that domain shift may still exist via label distribution shift at the classifier, thus deteriorating model performances. To alleviate this issue, we propose an approximate joint distribution matching scheme by exploiting prediction uncertainty. Specifically, we use a Bayesian neural network to quantify prediction uncertainty of a classifier. By imposing distribution matching on both features and labels (via uncertainty), label distribution mismatching in source and target data is effectively alleviated, encouraging the classifier to produce consistent predictions across domains. We also propose a few techniques to improve our method by adaptively reweighting domain adaptation loss to achieve nontrivial distribution matching and stable training. Comparisons with state of the art unsupervised domain adaptation methods on three popular benchmark datasets demonstrate the superiority of our approach, especially on the effectiveness of alleviating negative transfer.