# Dirichlet-based Uncertainty Calibration for Active Domain Adaptation

arXiv: https://arxiv.org/abs/2302.13824 · HTML: https://mlsanity.com/paper/2302.13824/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 58 references that are in the map.
- First posted on arXiv 27 Feb 2023.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2003.03773/) (2020)
- [Domain Adaptive Ensemble Learning](https://mlsanity.com/paper/2003.07325/) (2020)
- [Bayesian Neural Networks: An Introduction and Survey](https://mlsanity.com/paper/2006.12024/) (2020)
- [Evidential Deep Learning for Open Set Action Recognition](https://mlsanity.com/paper/2107.10161/) (2021)
- [Uncertainty Aware Semi-Supervised Learning on Graph Data](https://mlsanity.com/paper/2010.12783/) (2020)
- [Deep Active Learning: Unified and Principled Method for Query and Training](https://mlsanity.com/paper/1911.09162/) (2019)
- [Active Adversarial Domain Adaptation](https://mlsanity.com/paper/1904.07848/) (2019)
- [Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings](https://mlsanity.com/paper/2010.08666/) (2020)
- [Two-phase Pseudo Label Densification for Self-training based Domain Adaptation](https://mlsanity.com/paper/2012.04828/) (2020)
- [Active Learning for Domain Adaptation: An Energy-Based Approach](https://mlsanity.com/paper/2112.01406/) (2021)

## Built on by (most cited first, 24 of 24)

- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts](https://mlsanity.com/paper/2312.02567/) (2023)
- [Evidential Uncertainty Quantification: A Variance-Based Perspective](https://mlsanity.com/paper/2311.11367/) (2023)
- [Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2310.20293/) (2023)
- [Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty](https://mlsanity.com/paper/2404.10980/) (2024)
- [Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error](https://mlsanity.com/paper/2308.03003/) (2023)
- [Domain-Guided Conditional Diffusion Model for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2309.14360/) (2023)
- [Dirichlet-Based Prediction Calibration for Learning with Noisy Labels](https://mlsanity.com/paper/2401.07062/) (2024)
- [Uncertainty-aware Evidential Fusion-based Learning for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2404.06177/) (2024)
- [Unified modality separation: A vision-language framework for unsupervised domain adaptation](https://mlsanity.com/paper/2508.04987/) (2025)
- [Label Calibration in Source Free Domain Adaptation](https://mlsanity.com/paper/2501.07072/) (2025)
- [Human Scanpath Prediction in Target-Present Visual Search with Semantic-Foveal Bayesian Attention](https://mlsanity.com/paper/2507.18503/) (2025)
- [Semantic-Based Active Perception for Humanoid Visual Tasks with Foveal Sensors](https://mlsanity.com/paper/2404.10836/) (2024)
- [Source-free Active Domain Adaptation for Diabetic Retinopathy Grading Based on Ultra-wide-field Fundus Image](https://mlsanity.com/paper/2309.10619/) (2023)
- [Training-free image style alignment for self-adapting domain shift on handheld ultrasound devices](https://mlsanity.com/paper/2402.11211/) (2024)
- [Evidential Graph Contrastive Alignment for Source-Free Blending-Target Domain Adaptation](https://mlsanity.com/paper/2408.07527/) (2024)
- [Dirichlet-Based Coarse-to-Fine Example Selection For Open-Set Annotation](https://mlsanity.com/paper/2409.17607/) (2024)
- [Evidential Calibrated Uncertainty-Guided Interactive Segmentation paradigm for Ultrasound Images](https://mlsanity.com/paper/2501.01072/) (2025)
- [Adaptation Method for Misinformation Identification](https://mlsanity.com/paper/2504.14171/) (2025)
- [DAM: Dual Active Learning with Multimodal Foundation Model for Source-Free Domain Adaptation](https://mlsanity.com/paper/2509.24896/) (2025)
- [GALA: A GlobAl-LocAl Approach for Multi-Source Active Domain Adaptation](https://mlsanity.com/paper/2510.22214/) (2025)
- [EviATTA: Evidential Active Test-Time Adaptation for Medical Segment Anything Models](https://mlsanity.com/paper/2603.14666/) (2026)
- [BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation](https://mlsanity.com/paper/2605.17508/) (2026)
- [Improving Category-Aware Active Domain Adaptation via Uncertainty-Guided Region Coverage](https://mlsanity.com/paper/2610.19803/) (2026)

## Abstract (arXiv)

Active domain adaptation (DA) aims to maximally boost the model adaptation on a new target domain by actively selecting limited target data to annotate, whereas traditional active learning methods may be less effective since they do not consider the domain shift issue. Despite active DA methods address this by further proposing targetness to measure the representativeness of target domain characteristics, their predictive uncertainty is usually based on the prediction of deterministic models, which can easily be miscalibrated on data with distribution shift. Considering this, we propose a textitDirichlet-based Uncertainty Calibration (DUC) approach for active DA, which simultaneously achieves the mitigation of miscalibration and the selection of informative target samples. Specifically, we place a Dirichlet prior on the prediction and interpret the prediction as a distribution on the probability simplex, rather than a point estimate like deterministic models. This manner enables us to consider all possible predictions, mitigating the miscalibration of unilateral prediction. Then a two-round selection strategy based on different uncertainty origins is designed to select target samples that are both representative of target domain and conducive to discriminability. Extensive experiments on cross-domain image classification and semantic segmentation validate the superiority of DUC.