mlsanityData to 7 Oct 2026

Source-Free Domain Adaptation with Diffusion-Guided Source Data Generation

arXiv 2402.04929 ↗First posted 7 Feb 2024cs.CV cs.AI cs.LGcited by 4

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

This paper introduces a novel approach to leverage the generalizability of Diffusion Models for Source-Free Domain Adaptation (DM-SFDA). Our proposed DMSFDA method involves fine-tuning a pre-trained text-to-image diffusion model to generate source domain images using features from the target images to guide the diffusion process. Specifically, the pre-trained diffusion model is fine-tuned to generate source samples that minimize entropy and maximize confidence for the pre-trained source model. We then use a diffusion model-based image mixup strategy to bridge the domain gap between the source and target domains. We validate our approach through comprehensive experiments across a range of datasets, including Office-31, Office-Home, and VisDA. The results demonstrate significant improvements in SFDA performance, highlighting the potential of diffusion models in generating contextually relevant, domain-specific images.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 45 of its 56 references that are in the map. First posted on arXiv 7 Feb 2024.

Builds on

45 of 56 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Diffusion models as plug-and-play priors17 Jun
  2. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2023Visual Instruction Tuningcited by 7,792
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  8. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  9. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  10. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  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
31 more
  1. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  2. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  3. 2017VisDA: The Visual Domain Adaptation Challengecited by 432
  4. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 419
  5. 2015Return of Frustratingly Easy Domain Adaptationcited by 389
  6. 2023Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Modelscited by 371
  7. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  8. 2023Aligning Text-to-Image Diffusion Models with Reward Backpropagationcited by 284
  9. 2020Universal Source-Free Domain Adaptationcited by 219
  10. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  11. 2019Data-Free Learning of Student Networkscited by 203
  12. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 176
  13. 2020Universal Domain Adaptation through Self Supervisioncited by 172
  14. 2020Unsupervised Domain Adaptation via Structurally Regularized Deep Clusteringcited by 140
  15. 2020FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptationcited by 124
  16. 2021Predicting with Confidence on Unseen Distributionscited by 116
  17. 2021Source-free Domain Adaptation via Avatar Prototype Generation and Adaptationcited by 111
  18. 2022Source-Free Domain Adaptation via Distribution Estimationcited by 97
  19. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 93
  20. 2021Domain Impression: A Source Data Free Domain Adaptation Methodcited by 91
  21. 2020Maximum Density Divergence for Domain Adaptationcited by 76
  22. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 49
  23. 2023One-shot Unsupervised Domain Adaptation with Personalized Diffusion Modelscited by 35
  24. 2021Contrastive Vicinal Space for Unsupervised Domain Adaptationcited by 14
  25. 2022Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptationcited by 13
  26. 2023Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptationcited by 12
  27. 2023Gradual Source Domain Expansion for Unsupervised Domain Adaptationcited by 12
  28. 2017Conditional Adversarial Domain Adaptationcited by 10
  29. 2023Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clusteringcited by 9
  30. 2018Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptationcited by 6
  31. 2019Minimum Class Confusion for Versatile Domain Adaptationcited by 4

Built on by

Cited by year

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

4 papers.

  1. 2024ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfercited by 5
  2. 2025Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptationcited by 1
  3. 2025Source-Free Domain Adaptive Semantic Segmentation of Remote Sensing Images with Diffusion-Guided Label Enrichmentcited by 0
  4. 2025Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Transcending Domains through Text-to-Image Diffusion: A Source-Free Approach to Domain Adaptation
  2. 2023DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Data
  3. 2025When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class
  4. 2022Diffusion Guided Domain Adaptation of Image Generators
  5. 2026Revisiting Diffusion Fine-Tuning for Unsupervised Domain Adaptation
  6. 2024FDS: Feedback-guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain Generalization
  7. 2025Noise Optimized Conditional Diffusion for Domain Adaptation
  8. 2026VT-DUDA: Visual Token Conditioning for Diffusion-guided Unsupervised Domain Adaptation