mlsanityData to 14 Oct 2026

Confidence Score for Source-Free Unsupervised Domain Adaptation

arXiv 2206.06640 ↗First posted 14 Jun 2022cs.CV cs.LGcited by 59

Not on the map. Why?

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.

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

25 of 43 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  6. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  7. 2019When Does Label Smoothing Help?cited by 988
  8. 2017Selective Classification for Deep Neural Networkscited by 852
  9. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  10. 2018Learning to Reweight Examples for Robust Deep Learningcited by 675
  11. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 543
  12. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
13 more
  1. 2017VisDA: The Visual Domain Adaptation Challengecited by 435
  2. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  3. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  4. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 177
  5. 2018Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentationcited by 146
  6. 2020Unsupervised Domain Adaptation via Structurally Regularized Deep Clusteringcited by 140
  7. 2020FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptationcited by 124
  8. 2018Bias-Reduced Uncertainty Estimation for Deep Neural Classifierscited by 113
  9. 2017Partial Transfer Learning with Selective Adversarial Networkscited by 85
  10. 2020Progressive Graph Learning for Open-Set Domain Adaptationcited by 56
  11. 2020A Balanced and Uncertainty-aware Approach for Partial Domain Adaptationcited by 55
  12. 2021Visualizing Adapted Knowledge in Domain Transfercited by 32
  13. 2017Distance-based Confidence Score for Neural Network Classifierscited by 30

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 17; 2024: 19; 2025: 9; 2026: 11.

59 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  2. 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factorscited by 106
  3. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 80
  4. 2023Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptationcited by 65
  5. 2023On Pitfalls of Test-Time Adaptationcited by 64
  6. 2023Source-Free Domain Adaptation with Frozen Multimodal Foundation Modelcited by 55
  7. 2023Adversarial Alignment for Source Free Object Detectioncited by 25
  8. 2023UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentationcited by 21
  9. 2024Proxy Denoising for Source-Free Domain Adaptationcited by 21
  10. 2024SF(DA)2: Source-free Domain Adaptation Through the Lens of Data Augmentationcited by 19
  11. 2024A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Datacited by 15
  12. 2023Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memorycited by 11
38 more
  1. 2023Open-Set Domain Adaptation with Visual-Language Foundation Modelscited by 10
  2. 2023Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learningcited by 9
  3. 2023Context-Aware Pseudo-Label Refinement for Source-Free Domain Adaptive Fundus Image Segmentationcited by 7
  4. 2024Uncertainty-Aware Pseudo-Label Filtering for Source-Free Unsupervised Domain Adaptationcited by 7
  5. 2025Toward Robust Non-Transferable Learning: A Survey and Benchmarkcited by 7
  6. 2023Few-shot Fine-tuning is All You Need for Source-free Domain Adaptationcited by 6
  7. 2024Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Frameworkcited by 6
  8. 2023Aligning Non-Causal Factors for Transformer-Based Source-Free Domain Adaptationcited by 5
  9. 2024De-Confusing Pseudo-Labels in Source-Free Domain Adaptationcited by 5
  10. 2024Unified Source-Free Domain Adaptationcited by 5
  11. 2024Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptationcited by 4
  12. 2024Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Datacited by 4
  13. 2024Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learningcited by 3
  14. 2022Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptationcited by 2
  15. 2022Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptationcited by 2
  16. 2023Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain Adaptationcited by 2
  17. 2023Incorporating Pre-training Data Matters in Unsupervised Domain Adaptationcited by 2
  18. 2024STAG: Structural Test-time Alignment of Gradients for Online Adaptationcited by 2
  19. 2024Data-Efficient CLIP-Powered Dual-Branch Networks for Source-Free Unsupervised Domain Adaptationcited by 2
  20. 2025ViLAaD: Enhancing "Attracting and Dispersing'' Source-Free Domain Adaptation with Vision-and-Language Modelcited by 2
  21. 2025Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptationcited by 2
  22. 2023Confounder Balancing in Adversarial Domain Adaptation for Pre-Trained Large Models Fine-Tuningcited by 1
  23. 2024Source-Free Unsupervised Domain Adaptation with Hypothesis Consolidation of Prediction Rationalecited by 1
  24. 2024Domain Adaptive Diabetic Retinopathy Grading with Model Absence and Flowing Datacited by 1
  25. 2025Consistent Assistant Domains Transformer for Source-free Domain Adaptationcited by 1
  26. 2025Collaborative Learning with Multiple Foundation Models for Source-Free Domain Adaptationcited by 1
  27. 2026ProCal: Probability Calibration for Neighborhood-Guided Source-Free Domain Adaptationcited by 1
  28. 2026Source-Free Domain Adaptation with Vision-Language Priorcited by 1
  29. 2026Bridging Domain Expertise and Generalization for Performance Estimationcited by 1
  30. 2026Fairness-Aware Test-Time Prompt Tuningcited by 1
  31. 2023Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptationcited by 0
  32. 2023GeT: Generative Target Structure Debiasing for Domain Adaptationcited by 0
  33. 2024CNG-SFDA:Clean-and-Noisy Region Guided Online-Offline Source-Free Domain Adaptationcited by 0
  34. 2024High-order Neighborhoods Know More: HyperGraph Learning Meets Source-free Unsupervised Domain Adaptationcited by 0
  35. 2024EIANet: A Novel Domain Adaptation Approach to Maximize Class Distinction with Neural Collapse Principlescited by 0
  36. 2024DRIVE: Dual-Robustness via Information Variability and Entropic Consistency in Source-Free Unsupervised Domain Adaptationcited by 0
  37. 2025Context-Aware Self-Adaptation for Domain Generalizationcited by 0
  38. 2025OT Score: An OT based Confidence Score for Prototype-Assisted Source Free Unsupervised Domain Adaptationcited by 0

50 most cited of 59 All 59 (JSON)