# Transferable Calibration with Lower Bias and Variance in Domain Adaptation

arXiv: https://arxiv.org/abs/2007.08259 · HTML: https://mlsanity.com/paper/2007.08259/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2020.

## Built on by (most cited first, 30 of 41)

- [On Calibration and Out-of-domain Generalization](https://mlsanity.com/paper/2102.10395/) (2021)
- [Uncertainty Modeling for Out-of-Distribution Generalization](https://mlsanity.com/paper/2202.03958/) (2022)
- [PAC Prediction Sets Under Covariate Shift](https://mlsanity.com/paper/2106.09848/) (2021)
- [Robust Calibration with Multi-domain Temperature Scaling](https://mlsanity.com/paper/2206.02757/) (2022)
- [Confidence Calibration for Domain Generalization under Covariate Shift](https://mlsanity.com/paper/2104.00742/) (2021)
- [Source-Free Progressive Graph Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2202.06174/) (2022)
- [On Calibrating Semantic Segmentation Models: Analyses and An Algorithm](https://mlsanity.com/paper/2212.12053/) (2022)
- [Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2403.11491/) (2024)
- [Reliability in Semantic Segmentation: Are We on the Right Track?](https://mlsanity.com/paper/2303.11298/) (2023)
- [Beyond In-Domain Scenarios: Robust Density-Aware Calibration](https://mlsanity.com/paper/2302.05118/) (2023)
- [Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution](https://mlsanity.com/paper/2304.06537/) (2023)
- [Training on Test Data with Bayesian Adaptation for Covariate Shift](https://mlsanity.com/paper/2109.12746/) (2021)
- [Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling](https://mlsanity.com/paper/2206.01319/) (2022)
- [MaxEnt Loss: Constrained Maximum Entropy for Calibration under Out-of-Distribution Shift](https://mlsanity.com/paper/2310.17159/) (2023)
- [When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2509.16704/) (2025)
- [Decision-Making under Miscalibration](https://mlsanity.com/paper/2203.09852/) (2022)
- [Fast and Accurate Importance Weighting for Correcting Sample Bias](https://mlsanity.com/paper/2209.04215/) (2022)
- [Towards Calibrated Deep Clustering Network](https://mlsanity.com/paper/2403.02998/) (2024)
- [Optimizing Calibration by Gaining Aware of Prediction Correctness](https://mlsanity.com/paper/2404.13016/) (2024)
- [Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review](https://mlsanity.com/paper/2504.18346/) (2025)
- [Multiple-Source Domain Adaptation via Coordinated Domain Encoders and Paired Classifiers](https://mlsanity.com/paper/2201.11870/) (2022)
- [Modeling Uncertain Feature Representation for Domain Generalization](https://mlsanity.com/paper/2301.06442/) (2023)
- [AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images](https://mlsanity.com/paper/2312.06106/) (2023)
- [Fair Text Classification via Transferable Representations](https://mlsanity.com/paper/2503.07691/) (2025)
- [Confidence Calibration for Systems with Cascaded Predictive Modules](https://mlsanity.com/paper/2309.12510/) (2023)
- [On the Interconnections of Calibration, Quantification, and Classifier Accuracy Prediction under Dataset Shift](https://mlsanity.com/paper/2505.11380/) (2025)
- [Frustratingly Easy Uncertainty Estimation for Distribution Shift](https://mlsanity.com/paper/2106.03762/) (2021)
- [Adaptive Calibrator Ensemble for Model Calibration under Distribution Shift](https://mlsanity.com/paper/2303.05331/) (2023)
- [IW-GAE: Importance Weighted Group Accuracy Estimation for Improved Calibration and Model Selection in Unsupervised Domain Adaptation](https://mlsanity.com/paper/2310.10611/) (2023)
- [Domain-adaptive and Subgroup-specific Cascaded Temperature Regression for Out-of-distribution Calibration](https://mlsanity.com/paper/2402.09204/) (2024)

## Abstract (arXiv)

Domain Adaptation (DA) enables transferring a learning machine from a labeled source domain to an unlabeled target one. While remarkable advances have been made, most of the existing DA methods focus on improving the target accuracy at inference. How to estimate the predictive uncertainty of DA models is vital for decision-making in safety-critical scenarios but remains the boundary to explore. In this paper, we delve into the open problem of Calibration in DA, which is extremely challenging due to the coexistence of domain shift and the lack of target labels. We first reveal the dilemma that DA models learn higher accuracy at the expense of well-calibrated probabilities. Driven by this finding, we propose Transferable Calibration (TransCal) to achieve more accurate calibration with lower bias and variance in a unified hyperparameter-free optimization framework. As a general post-hoc calibration method, TransCal can be easily applied to recalibrate existing DA methods. Its efficacy has been justified both theoretically and empirically.