# Confidence Score for Source-Free Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2206.06640 · HTML: https://mlsanity.com/paper/2206.06640/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 14 Jun 2022.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation](https://mlsanity.com/paper/1808.01200/) (2018)
- [Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering](https://mlsanity.com/paper/2003.08607/) (2020)
- [FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2011.09230/) (2020)
- [Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers](https://mlsanity.com/paper/1805.08206/) (2018)
- [Partial Transfer Learning with Selective Adversarial Networks](https://mlsanity.com/paper/1707.07901/) (2017)
- [Progressive Graph Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2006.12087/) (2020)
- [A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation](https://mlsanity.com/paper/2003.02541/) (2020)
- [Visualizing Adapted Knowledge in Domain Transfer](https://mlsanity.com/paper/2104.10602/) (2021)
- [Distance-based Confidence Score for Neural Network Classifiers](https://mlsanity.com/paper/1709.09844/) (2017)

## Built on by (most cited first, 30 of 59)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors](https://mlsanity.com/paper/2403.07366/) (2024)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2303.03770/) (2023)
- [On Pitfalls of Test-Time Adaptation](https://mlsanity.com/paper/2306.03536/) (2023)
- [Source-Free Domain Adaptation with Frozen Multimodal Foundation Model](https://mlsanity.com/paper/2311.16510/) (2023)
- [Adversarial Alignment for Source Free Object Detection](https://mlsanity.com/paper/2301.04265/) (2023)
- [UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2309.10244/) (2023)
- [Proxy Denoising for Source-Free Domain Adaptation](https://mlsanity.com/paper/2406.01658/) (2024)
- [SF(DA)2: Source-free Domain Adaptation Through the Lens of Data Augmentation](https://mlsanity.com/paper/2403.10834/) (2024)
- [A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data](https://mlsanity.com/paper/2407.02112/) (2024)
- [Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memory](https://mlsanity.com/paper/2308.13236/) (2023)
- [Open-Set Domain Adaptation with Visual-Language Foundation Models](https://mlsanity.com/paper/2307.16204/) (2023)
- [Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning](https://mlsanity.com/paper/2306.01598/) (2023)
- [Context-Aware Pseudo-Label Refinement for Source-Free Domain Adaptive Fundus Image Segmentation](https://mlsanity.com/paper/2308.07731/) (2023)
- [Uncertainty-Aware Pseudo-Label Filtering for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2403.11256/) (2024)
- [Toward Robust Non-Transferable Learning: A Survey and Benchmark](https://mlsanity.com/paper/2502.13593/) (2025)
- [Few-shot Fine-tuning is All You Need for Source-free Domain Adaptation](https://mlsanity.com/paper/2304.00792/) (2023)
- [Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Framework](https://mlsanity.com/paper/2411.12558/) (2024)
- [Aligning Non-Causal Factors for Transformer-Based Source-Free Domain Adaptation](https://mlsanity.com/paper/2311.16294/) (2023)
- [De-Confusing Pseudo-Labels in Source-Free Domain Adaptation](https://mlsanity.com/paper/2401.01650/) (2024)
- [Unified Source-Free Domain Adaptation](https://mlsanity.com/paper/2403.07601/) (2024)
- [Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation](https://mlsanity.com/paper/2403.10911/) (2024)
- [Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data](https://mlsanity.com/paper/2412.13757/) (2024)
- [Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learning](https://mlsanity.com/paper/2405.18376/) (2024)
- [Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptation](https://mlsanity.com/paper/2212.03795/) (2022)
- [Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation](https://mlsanity.com/paper/2212.08187/) (2022)
- [Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain Adaptation](https://mlsanity.com/paper/2301.13428/) (2023)
- [Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation](https://mlsanity.com/paper/2308.03097/) (2023)
- [STAG: Structural Test-time Alignment of Gradients for Online Adaptation](https://mlsanity.com/paper/2402.09004/) (2024)

## Abstract (arXiv)

Source-free unsupervised domain adaptation (SFUDA) aims to obtain high performance in the unlabeled target domain using the pre-trained source model, not the source data. Existing SFUDA methods assign the same importance to all target samples, which is vulnerable to incorrect pseudo-labels. To differentiate between sample importance, in this study, we propose a novel sample-wise confidence score, the Joint Model-Data Structure (JMDS) score for SFUDA. Unlike existing confidence scores that use only one of the source or target domain knowledge, the JMDS score uses both knowledge. We then propose a Confidence score Weighting Adaptation using the JMDS (CoWA-JMDS) framework for SFUDA. CoWA-JMDS consists of the JMDS scores as sample weights and weight Mixup that is our proposed variant of Mixup. Weight Mixup promotes the model make more use of the target domain knowledge. The experimental results show that the JMDS score outperforms the existing confidence scores. Moreover, CoWA-JMDS achieves state-of-the-art performance on various SFUDA scenarios: closed, open, and partial-set scenarios.