mlsanityData to 14 Oct 2026

OneRing: A Simple Method for Source-free Open-partial Domain Adaptation

arXiv 2206.03600 ↗First posted 7 Jun 2022cs.CV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

In this paper, we investigate Source-free Open-partial Domain Adaptation (SF-OPDA), which addresses the situation where there exist both domain and category shifts between source and target domains. Under the SF-OPDA setting, which aims to address data privacy concerns, the model cannot access source data anymore during target adaptation. We propose a novel training scheme to learn a (n+1)-way classifier to predict the n source classes and the unknown class, where samples of only known source categories are available for training. Furthermore, for target adaptation, we simply adopt a weighted entropy minimization to adapt the source pretrained model to the unlabeled target domain without source data. In experiments, we show our simple method surpasses current OPDA approaches which demand source data during adaptation. When augmented with a closed-set domain adaptation approach during target adaptation, our source-free method further outperforms the current state-of-the-art OPDA method by 2.5%, 7.2% and 13% on Office-31, Office-Home and VisDA respectively.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 52 of its 73 references that are in the map. First posted on arXiv 7 Jun 2022.

Builds on

52 of 73 references.

References · 52

  1. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  2. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  3. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  4. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  5. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  6. 2020In Search of Lost Domain Generalizationcited by 1,054
  7. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  8. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
  9. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  10. 2017VisDA: The Visual Domain Adaptation Challengecited by 435
  11. 2015Return of Frustratingly Easy Domain Adaptationcited by 391
  12. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
38 more
  1. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 341
  2. 2021Gradient Matching for Domain Generalizationcited by 258
  3. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  4. 2020Universal Source-Free Domain Adaptationcited by 220
  5. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  6. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 177
  7. 2021Generalized Source-free Domain Adaptationcited by 175
  8. 2020Universal Domain Adaptation through Self Supervisioncited by 172
  9. 2021Learning to Diversify for Single Domain Generalizationcited by 170
  10. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  11. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  12. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  13. 2018Open Set Domain Adaptation by Backpropagationcited by 150
  14. 2020Unsupervised Domain Adaptation via Structurally Regularized Deep Clusteringcited by 140
  15. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  16. 2020Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situationscited by 133
  17. 2018Partial Adversarial Domain Adaptationcited by 127
  18. 2021Learning Placeholders for Open-Set Recognitioncited by 121
  19. 2019Domain-Symmetric Networks for Adversarial Domain Adaptationcited by 120
  20. 2021Cycle Self-Training for Domain Adaptationcited by 120
  21. 2020Learning Open Set Network with Discriminative Reciprocal Pointscited by 115
  22. 2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
  23. 2020Hybrid Models for Open Set Recognitioncited by 109
  24. 2020Conditional Gaussian Distribution Learning for Open Set Recognitioncited by 104
  25. 2021Model-Based Domain Generalizationcited by 104
  26. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 94
  27. 2021OVANet: One-vs-All Network for Universal Domain Adaptationcited by 92
  28. 2019Cluster Alignment with a Teacher for Unsupervised Domain Adaptationcited by 88
  29. 2019Learning to Transfer Examples for Partial Domain Adaptationcited by 87
  30. 2020Domain Adaptation with Auxiliary Target Domain-Oriented Classifiercited by 76
  31. 2020On the Effectiveness of Image Rotation for Open Set Domain Adaptationcited by 72
  32. 2020Towards Inheritable Models for Open-Set Domain Adaptationcited by 64
  33. 2020A Balanced and Uncertainty-aware Approach for Partial Domain Adaptationcited by 55
  34. 2019Unsupervised Domain Adaptation via Regularized Conditional Alignmentcited by 34
  35. 2019P-ODN: Prototype based Open Deep Network for Open Set Recognitioncited by 28
  36. 2020Exploring Category-Agnostic Clusters for Open-Set Domain Adaptationcited by 27
  37. 2021UMAD: Universal Model Adaptation under Domain and Category Shiftcited by 23
  38. 2019Attract or Distract: Exploit the Margin of Open Setcited by 13

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

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

3 papers.

  1. 2025Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptationcited by 4
  2. 2024Unveiling the Superior Paradigm: A Comparative Study of Source-Free Domain Adaptation and Unsupervised Domain Adaptationcited by 0
  3. 2026oslash Source Models Leak What They Shouldn't nrightarrow: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimizationcited by 0