mlsanityData to 7 Oct 2026

Domain Impression: A Source Data Free Domain Adaptation Method

arXiv 2102.09003 ↗First posted 17 Feb 2021cs.CV cs.AIcited by 91

Not on the map. Why?

Abstract (arXiv)

Unsupervised Domain adaptation methods solve the adaptation problem for an unlabeled target set, assuming that the source dataset is available with all labels. However, the availability of actual source samples is not always possible in practical cases. It could be due to memory constraints, privacy concerns, and challenges in sharing data. This practical scenario creates a bottleneck in the domain adaptation problem. This paper addresses this challenging scenario by proposing a domain adaptation technique that does not need any source data. Instead of the source data, we are only provided with a classifier that is trained on the source data. Our proposed approach is based on a generative framework, where the trained classifier is used for generating samples from the source classes. We learn the joint distribution of data by using the energy-based modeling of the trained classifier. At the same time, a new classifier is also adapted for the target domain. We perform various ablation analysis under different experimental setups and demonstrate that the proposed approach achieves better results than the baseline models in this extremely novel scenario.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). Builds on 48 of its 75 references that are in the map. First posted on arXiv 17 Feb 2021.

Builds on

48 of 75 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2014Conditional Generative Adversarial Netscited by 2,152
  5. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  7. 2016Adversarial examples in the physical worldcited by 1,762
  8. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  10. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  11. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  12. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
36 more
  1. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  2. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  3. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  4. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  5. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  6. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 419
  7. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  8. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  9. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 280
  10. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  11. 2020Universal Source-Free Domain Adaptationcited by 219
  12. 2019Data-Free Learning of Student Networkscited by 203
  13. 2018Multi-Adversarial Domain Adaptationcited by 195
  14. 2017Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learningcited by 192
  15. 2017Generate To Adapt: Aligning Domains using Generative Adversarial Networkscited by 183
  16. 2017Asymmetric Tri-training for Unsupervised Domain Adaptationcited by 152
  17. 2017Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptationcited by 151
  18. 2019Federated Adversarial Domain Adaptationcited by 140
  19. 2019Zero-Shot Knowledge Distillation in Deep Networkscited by 119
  20. 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
  21. 2018Generalizable Data-free Objective for Crafting Universal Adversarial Perturbationscited by 88
  22. 2019Discriminative Adversarial Domain Adaptationcited by 74
  23. 2020Adversarial-Learned Loss for Domain Adaptationcited by 65
  24. 2017A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoderscited by 64
  25. 2019Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptationcited by 62
  26. 2017Adversarial Feature Augmentation for Unsupervised Domain Adaptationcited by 48
  27. 2018Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptationcited by 45
  28. 2019Attending to Discriminative Certainty for Domain Adaptationcited by 37
  29. 2019Unsupervised Domain Adaptation via Regularized Conditional Alignmentcited by 34
  30. 2018Image Colorization with Generative Adversarial Networkscited by 24
  31. 2019Bayesian Uncertainty Matching for Unsupervised Domain Adaptationcited by 22
  32. 2019DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifiercited by 21
  33. 2019Cycle-consistent Conditional Adversarial Transfer Networkscited by 15
  34. 2019Looking back at Labels: A Class based Domain Adaptation Techniquecited by 11
  35. 2018Visual Data Synthesis via GAN for Zero-Shot Video Classificationcited by 10
  36. 2019Curriculum based Dropout Discriminator for Domain Adaptationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 22; 2023: 28; 2024: 14; 2025: 10; 2026: 5.

91 papers.

Sort:

By area:

  1. 2022Continual Test-Time Domain Adaptationcited by 520
  2. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  3. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  4. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  5. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  6. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  7. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
  8. 2021Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformationcited by 67
  9. 2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
  10. 2023Source-Free Domain Adaptation with Frozen Multimodal Foundation Modelcited by 54
  11. 2022GradViT: Gradient Inversion of Vision Transformerscited by 52
  12. 2022Source-free Depth for Object Pop-outcited by 52
38 more
  1. 2021Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restorationcited by 50
  2. 2022Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Expertscited by 50
  3. 2021Data-Free Knowledge Transfer: A Surveycited by 31
  4. 2023Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptationcited by 31
  5. 2023POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained modelscited by 29
  6. 2021Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptationcited by 28
  7. 2022Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognitioncited by 28
  8. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  9. 2022Source-Free Progressive Graph Learning for Open-Set Domain Adaptationcited by 25
  10. 2021UMAD: Universal Model Adaptation under Domain and Category Shiftcited by 23
  11. 2022CoNMix for Source-free Single and Multi-target Domain Adaptationcited by 23
  12. 2022CAFA: Class-Aware Feature Alignment for Test-Time Adaptationcited by 21
  13. 2023Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shiftscited by 21
  14. 2024Proxy Denoising for Source-Free Domain Adaptationcited by 20
  15. 2021Unsupervised Robust Domain Adaptation without Source Datacited by 19
  16. 2021Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Surveycited by 19
  17. 2024Active Test-Time Adaptation: Theoretical Analyses and An Algorithmcited by 18
  18. 2022On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptationcited by 16
  19. 2022Few-Shot Adaptation of Pre-Trained Networks for Domain Shiftcited by 16
  20. 2023The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptationcited by 16
  21. 2023Source-Free Domain Adaptation with Temporal Imputation for Time Series Datacited by 15
  22. 2023Source-free Domain Adaptive Human Pose Estimationcited by 15
  23. 2022Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptationcited by 14
  24. 2023Energy-Based Test Sample Adaptation for Domain Generalizationcited by 14
  25. 2022Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptationcited by 13
  26. 2024Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streamscited by 13
  27. 2021Secure Domain Adaptation with Multiple Sourcescited by 12
  28. 2022Continual BatchNorm Adaptation (CBNA) for Semantic Segmentationcited by 12
  29. 2023In Search for a Generalizable Method for Source Free Domain Adaptationcited by 12
  30. 2023Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memorycited by 11
  31. 2022SALAD: Source-free Active Label-Agnostic Domain Adaptation for Classification, Segmentation and Detectioncited by 10
  32. 2022RAIN: RegulArization on Input and Network for Black-Box Domain Adaptationcited by 9
  33. 2022Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptationcited by 9
  34. 2022Anatomy-guided domain adaptation for 3D in-bed human pose estimationcited by 9
  35. 2024Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histologycited by 9
  36. 2025Disentangled Source-Free Personalization for Facial Expression Recognition with Neutral Target Datacited by 9
  37. 2025Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Methodcited by 8
  38. 2023Few-shot Fine-tuning is All You Need for Source-free Domain Adaptationcited by 6

50 most cited of 91 All 91 (JSON)