mlsanityData to 7 Oct 2026

A Prototype-Oriented Framework for Unsupervised Domain Adaptation

arXiv 2110.12024 ↗First posted 22 Oct 2021cs.LG cs.CV stat.MLcited by 62

Not on the map. Why?

Abstract (arXiv)

Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space. To avoid the sampling variability, class imbalance, and data-privacy concerns that often plague these methods, we instead provide a memory and computation-efficient probabilistic framework to extract class prototypes and align the target features with them. We demonstrate the general applicability of our method on a wide range of scenarios, including single-source, multi-source, class-imbalance, and source-private domain adaptation. Requiring no additional model parameters and having a moderate increase in computation over the source model alone, the proposed method achieves competitive performance with state-of-the-art methods.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). Builds on 46 of its 90 references that are in the map. First posted on arXiv 22 Oct 2021.

Builds on

46 of 90 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  5. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  6. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  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. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  11. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  12. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
34 more
  1. 2018Computational Optimal Transportcited by 765
  2. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  3. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  4. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  5. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  6. 2019Self-labelling via simultaneous clustering and representation learningcited by 525
  7. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  8. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 364
  9. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  10. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 333
  11. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  12. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 280
  13. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  14. 2020Universal Source-Free Domain Adaptationcited by 219
  15. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  16. 2018DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptationcited by 212
  17. 2020Universal Domain Adaptation through Self Supervisioncited by 172
  18. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  19. 2019Transferrable Prototypical Networks for Unsupervised Domain Adaptationcited by 141
  20. 2020Domain Adaptation with Conditional Distribution Matching and Generalized Label Shiftcited by 124
  21. 2019Regularized Learning for Domain Adaptation under Label Shiftscited by 118
  22. 2018Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shiftcited by 109
  23. 2021Domain Impression: A Source Data Free Domain Adaptation Methodcited by 91
  24. 2019Support and Invertibility in Domain-Invariant Representationscited by 87
  25. 2015A Deeper Look at Dataset Biascited by 86
  26. 2020Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptationcited by 86
  27. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  28. 2017Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptationcited by 70
  29. 2021Your Classifier can Secretly Suffice Multi-Source Domain Adaptationcited by 42
  30. 2018Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximizationcited by 40
  31. 2020Class-Incremental Domain Adaptationcited by 36
  32. 2018MONK -- Outlier-Robust Mean Embedding Estimation by Median-of-Meanscited by 9
  33. 2020Entropy Minimization vs. Diversity Maximization for Domain Adaptationcited by 8
  34. 2020Mutual Learning Network for Multi-Source Domain Adaptationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 29; 2024: 18; 2025: 5; 2026: 5.

62 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  3. 2023Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspectivecited by 54
  4. 2023Source-Free Domain Adaptation with Frozen Multimodal Foundation Modelcited by 54
  5. 2024FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learningcited by 47
  6. 2023When Source-Free Domain Adaptation Meets Learning with Noisy Labelscited by 46
  7. 2022BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptationcited by 39
  8. 2022Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddingscited by 36
  9. 2022ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptationcited by 34
  10. 2024Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimizationcited by 30
  11. 2023POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained modelscited by 29
  12. 2024Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domainscited by 27
38 more
  1. 2024Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Modelscited by 22
  2. 2023PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classificationcited by 21
  3. 2024Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Datacited by 21
  4. 2024Proxy Denoising for Source-Free Domain Adaptationcited by 20
  5. 2024CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detectioncited by 19
  6. 2023Dual Adaptive Representation Alignment for Cross-domain Few-shot Learningcited by 15
  7. 2023Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learningcited by 14
  8. 2023Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variantscited by 14
  9. 2024Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Framecited by 14
  10. 2023DEJA VU: Continual Model Generalization For Unseen Domainscited by 13
  11. 2023Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Modelscited by 12
  12. 2024Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptationcited by 10
  13. 2022CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domainscited by 9
  14. 2023Imbalanced Open Set Domain Adaptation via Moving-threshold Estimation and Gradual Alignmentcited by 9
  15. 2023Concept Distillation: Leveraging Human-Centered Explanations for Model Improvementcited by 9
  16. 2023Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentationcited by 8
  17. 2023GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Cloudscited by 8
  18. 2024Enhancing Domain Adaptation through Prompt Gradient Alignmentcited by 8
  19. 2023CAME: Contrastive Automated Model Evaluationcited by 6
  20. 2024TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learningcited by 6
  21. 2024CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysiscited by 6
  22. 2022Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representationscited by 5
  23. 2024Enhancing Test Time Adaptation with Few-shot Guidancecited by 5
  24. 2025Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofingcited by 5
  25. 2023Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptationcited by 4
  26. 2023Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptationcited by 3
  27. 2023Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localizationcited by 3
  28. 2023CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shiftcited by 3
  29. 2023Single Image Test-Time Adaptation for Segmentationcited by 3
  30. 2023A Prototype-Oriented Clustering for Domain Shift with Source Privacycited by 2
  31. 2024Advancing Prompt Learning through an External Layercited by 2
  32. 2023Multi-Domain Learning From Insufficient Annotationscited by 1
  33. 2023A Study of Unsupervised Evaluation Metrics for Practical and Automatic Domain Adaptationcited by 1
  34. 2024Layer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Taskscited by 1
  35. 2024Prototype-based Optimal Transport for Out-of-Distribution Detectioncited by 1
  36. 2026Source-Free Domain Adaptation for Geospatial Point Cloud Semantic Segmentationcited by 1
  37. 2026Source-Free Domain Adaptation with Vision-Language Priorcited by 1
  38. 2026Temporal Structure Matters for Efficient Test-Time Adaptation in Wearable Human Activity Recognitioncited by 1

50 most cited of 62 All 62 (JSON)