mlsanityData to 7 Oct 2026

De-Confusing Pseudo-Labels in Source-Free Domain Adaptation

arXiv 2401.01650 ↗First posted 3 Jan 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Source-free domain adaptation aims to adapt a source-trained model to an unlabeled target domain without access to the source data. It has attracted growing attention in recent years, where existing approaches focus on self-training that usually includes pseudo-labeling techniques. In this paper, we introduce a novel noise-learning approach tailored to address noise distribution in domain adaptation settings and learn to de-confuse the pseudo-labels. More specifically, we learn a noise transition matrix of the pseudo-labels to capture the label corruption of each class and learn the underlying true label distribution. Estimating the noise transition matrix enables a better true class-posterior estimation, resulting in better prediction accuracy. We demonstrate the effectiveness of our approach when combined with several source-free domain adaptation methods: SHOT, SHOT++, and AaD. We obtain state-of-the-art results on three domain adaptation datasets: VisDA, DomainNet, and OfficeHome.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 53 of its 66 references that are in the map. First posted on arXiv 3 Jan 2024.

Builds on

53 of 66 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  5. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  6. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  7. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  8. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  9. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  10. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  11. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  12. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
38 more
  1. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  2. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  3. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  4. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  5. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
  6. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 441
  7. 2017VisDA: The Visual Domain Adaptation Challengecited by 432
  8. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  9. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  10. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  11. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 214
  12. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 176
  13. 2021Generalized Source-free Domain Adaptationcited by 175
  14. 2020Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfercited by 173
  15. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  16. 2019Learning From Noisy Labels By Regularized Estimation Of Annotator Confusioncited by 126
  17. 2019Unsupervised Domain Adaptation through Self-Supervisioncited by 116
  18. 2021Source-free Domain Adaptation via Avatar Prototype Generation and Adaptationcited by 111
  19. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  20. 2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
  21. 2022Source-Free Domain Adaptation via Distribution Estimationcited by 97
  22. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 93
  23. 2017Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptationcited by 70
  24. 2022A Broad Study of Pre-training for Domain Generalization and Adaptationcited by 64
  25. 2023Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptationcited by 63
  26. 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
  27. 2019Self-supervised Domain Adaptation for Computer Vision Taskscited by 58
  28. 2022Confidence Score for Source-Free Unsupervised Domain Adaptationcited by 58
  29. 2022Balancing Discriminability and Transferability for Source-Free Domain Adaptationcited by 58
  30. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 49
  31. 2021Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptationcited by 47
  32. 2022Uncertainty-guided Source-free Domain Adaptationcited by 46
  33. 2023When Source-Free Domain Adaptation Meets Learning with Noisy Labelscited by 46
  34. 2022BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptationcited by 39
  35. 2020Rethinking Distributional Matching Based Domain Adaptationcited by 33
  36. 2022CoNMix for Source-free Single and Multi-target Domain Adaptationcited by 23
  37. 2022Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptationcited by 21
  38. 2023Learning from Noisy Labels with Decoupled Meta Label Purifiercited by 21

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 3.

5 papers.

  1. 2024Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learningcited by 3
  2. 2025ViLAaD: Enhancing "Attracting and Dispersing'' Source-Free Domain Adaptation with Vision-and-Language Modelcited by 2
  3. 2026Generalization Under Scrutiny: Cross-Domain Detection Progresses, Pitfalls, and Persistent Challengescited by 0
  4. 2026Rethinking the Need for Source Models: Source-Free Domain Adaptation from Scratch Guided by a Vision-Language Modelcited by 0
  5. 2026LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptationcited by 0