# Label Calibration in Source Free Domain Adaptation

arXiv: https://arxiv.org/abs/2501.07072 · HTML: https://mlsanity.com/paper/2501.07072/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 37 references that are in the map.
- First posted on arXiv 13 Jan 2025.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Evidential Deep Learning for Open Set Action Recognition](https://mlsanity.com/paper/2107.10161/) (2021)
- [Domain Impression: A Source Data Free Domain Adaptation Method](https://mlsanity.com/paper/2102.09003/) (2021)
- [Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation](https://mlsanity.com/paper/2110.03051/) (2021)
- [Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2303.03770/) (2023)
- [Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling](https://mlsanity.com/paper/2109.09735/) (2021)
- [Uncertainty Estimation by Fisher Information-based Evidential Deep Learning](https://mlsanity.com/paper/2303.02045/) (2023)
- [Uncertainty-guided Source-free Domain Adaptation](https://mlsanity.com/paper/2208.07591/) (2022)
- [Transformer-Based Source-Free Domain Adaptation](https://mlsanity.com/paper/2105.14138/) (2021)
- [Learn to Accumulate Evidence from All Training Samples: Theory and Practice](https://mlsanity.com/paper/2306.11113/) (2023)
- [Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts](https://mlsanity.com/paper/2312.02567/) (2023)
- [Dirichlet-based Uncertainty Calibration for Active Domain Adaptation](https://mlsanity.com/paper/2302.13824/) (2023)
- [UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2309.10244/) (2023)
- [Prior Knowledge Guided Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.08877/) (2022)
- [Unsupervised Domain Adaptation via Calibrating Uncertainties](https://mlsanity.com/paper/1907.11202/) (2019)
- [Prior-guided Source-free Domain Adaptation for Human Pose Estimation](https://mlsanity.com/paper/2308.13954/) (2023)
- [Continual Evidential Deep Learning for Out-of-Distribution Detection](https://mlsanity.com/paper/2309.02995/) (2023)
- [Dirichlet-Based Prediction Calibration for Learning with Noisy Labels](https://mlsanity.com/paper/2401.07062/) (2024)
- [Unsupervised Domain Adaptation Based on the Predictive Uncertainty of Models](https://mlsanity.com/paper/2211.08866/) (2022)

## Built on by (most cited first, 3 of 3)

- [ViLAaD: Enhancing "Attracting and Dispersing'' Source-Free Domain Adaptation with Vision-and-Language Model](https://mlsanity.com/paper/2503.23529/) (2025)
- [Grad-CL: Source Free Domain Adaptation with Gradient Guided Feature Disalignment](https://mlsanity.com/paper/2509.10134/) (2025)
- [Source-Free Domain Adaptation with Vision-Language Prior](https://mlsanity.com/paper/2604.17748/) (2026)

## Abstract (arXiv)

Source-free domain adaptation (SFDA) utilizes a pre-trained source model with unlabeled target data. Self-supervised SFDA techniques generate pseudolabels from the pre-trained source model, but these pseudolabels often contain noise due to domain discrepancies between the source and target domains. Traditional self-supervised SFDA techniques rely on deterministic model predictions using the softmax function, leading to unreliable pseudolabels. In this work, we propose to introduce predictive uncertainty and softmax calibration for pseudolabel refinement using evidential deep learning. The Dirichlet prior is placed over the output of the target network to capture uncertainty using evidence with a single forward pass. Furthermore, softmax calibration solves the translation invariance problem to assist in learning with noisy labels. We incorporate a combination of evidential deep learning loss and information maximization loss with calibrated softmax in both prior and non-prior target knowledge SFDA settings. Extensive experimental analysis shows that our method outperforms other state-of-the-art methods on benchmark datasets.