mlsanityData to 7 Oct 2026

Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation

arXiv 2002.08546 ↗First posted 20 Feb 2020cs.CV cs.LGcited by 844

Not on the map. Why?

Cited by 25 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA methods typically require to access the source data when learning to adapt the model, making them risky and inefficient for decentralized private data. This work tackles a practical setting where only a trained source model is available and investigates how we can effectively utilize such a model without source data to solve UDA problems. We propose a simple yet generic representation learning framework, named Source HypOthesis Transfer (SHOT). SHOT freezes the classifier module (hypothesis) of the source model and learns the target-specific feature extraction module by exploiting both information maximization and self-supervised pseudo-labeling to implicitly align representations from the target domains to the source hypothesis. To verify its versatility, we evaluate SHOT in a variety of adaptation cases including closed-set, partial-set, and open-set domain adaptation. Experiments indicate that SHOT yields state-of-the-art results among multiple domain adaptation benchmarks.

Key facts. Cited by 844 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 102; 2022: 135; 2023: 195; 2024: 182; 2025: 130; 2026: 100.

844 papers.

Sort:

By area:

  1. 2022Continual Test-Time Domain Adaptationcited by 520
  2. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  3. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
  4. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 379
  5. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  6. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 351
  7. 2022Contrastive Test-Time Adaptationcited by 258
  8. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  9. 2022Parameter-free Online Test-time Adaptationcited by 184
  10. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 176
  11. 2021Generalized Source-free Domain Adaptationcited by 175
  12. 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
38 more
  1. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  2. 2022Knowledge Distillation with the Reused Teacher Classifiercited by 140
  3. 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
  4. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
  5. 2021Source-free Domain Adaptation via Avatar Prototype Generation and Adaptationcited by 111
  6. 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factorscited by 106
  7. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  8. 2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 102
  9. 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
  10. 2021On Interaction Between Augmentations and Corruptions in Natural Corruption Robustnesscited by 98
  11. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  12. 2022Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptationcited by 98
  13. 2022Source-Free Domain Adaptation via Distribution Estimationcited by 97
  14. 2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
  15. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 93
  16. 2021Domain Impression: A Source Data Free Domain Adaptation Methodcited by 91
  17. 2022SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentationcited by 87
  18. 2021TVT: Transferable Vision Transformer for Unsupervised Domain Adaptationcited by 81
  19. 2021Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentationcited by 81
  20. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
  21. 2022Deep Clustering: A Comprehensive Surveycited by 78
  22. 2021Unsupervised Multi-source Domain Adaptation Without Access to Source Datacited by 76
  23. 2021Cross-domain Contrastive Learning for Unsupervised Domain Adaptationcited by 75
  24. 2023DELTA: degradation-free fully test-time adaptationcited by 72
  25. 2022Back to the Source: Diffusion-Driven Test-Time Adaptationcited by 71
  26. 2021VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptationcited by 69
  27. 2021Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptationcited by 67
  28. 2021Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformationcited by 67
  29. 2022Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypescited by 67
  30. 2023Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correctioncited by 65
  31. 2022Test-Time Adaptation via Self-Training with Nearest Neighbor Informationcited by 64
  32. 2023Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptationcited by 63
  33. 2023On Pitfalls of Test-Time Adaptationcited by 63
  34. 2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
  35. 2022Safe Self-Refinement for Transformer-based Domain Adaptationcited by 61
  36. 2022Confidence Score for Source-Free Unsupervised Domain Adaptationcited by 58
  37. 2022Balancing Discriminability and Transferability for Source-Free Domain Adaptationcited by 58
  38. 2023ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptationcited by 58

50 most cited of 844 All 844 (JSON)