mlsanityData to 7 Oct 2026

Your Classifier can Secretly Suffice Multi-Source Domain Adaptation

arXiv 2103.11169 ↗First posted 20 Mar 2021cs.LG cs.CVcited by 42

Not on the map. Why?

Abstract (arXiv)

Multi-Source Domain Adaptation (MSDA) deals with the transfer of task knowledge from multiple labeled source domains to an unlabeled target domain, under a domain-shift. Existing methods aim to minimize this domain-shift using auxiliary distribution alignment objectives. In this work, we present a different perspective to MSDA wherein deep models are observed to implicitly align the domains under label supervision. Thus, we aim to utilize implicit alignment without additional training objectives to perform adaptation. To this end, we use pseudo-labeled target samples and enforce a classifier agreement on the pseudo-labels, a process called Self-supervised Implicit Alignment (SImpAl). We find that SImpAl readily works even under category-shift among the source domains. Further, we propose classifier agreement as a cue to determine the training convergence, resulting in a simple training algorithm. We provide a thorough evaluation of our approach on five benchmarks, along with detailed insights into each component of our approach.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 47 of its 72 references that are in the map. First posted on arXiv 20 Mar 2021.

Builds on

47 of 72 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  8. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  9. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  10. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  11. 2014How transferable are features in deep neural networks?cited by 1,216
  12. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
35 more
  1. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  2. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  3. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  4. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  5. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  6. 2019Confidence Regularized Self-Trainingcited by 418
  7. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  8. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  9. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  10. 2020Universal Source-Free Domain Adaptationcited by 219
  11. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 205
  12. 2019Domain-Specific Batch Normalization for Unsupervised Domain Adaptationcited by 197
  13. 2018Multi-Adversarial Domain Adaptationcited by 195
  14. 2017Generate To Adapt: Aligning Domains using Generative Adversarial Networkscited by 183
  15. 2020Universal Domain Adaptation through Self Supervisioncited by 172
  16. 2017Image to Image Translation for Domain Adaptationcited by 171
  17. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  18. 2017Asymmetric Tri-training for Unsupervised Domain Adaptationcited by 152
  19. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  20. 2018Open Set Domain Adaptation by Backpropagationcited by 150
  21. 2019Transferrable Prototypical Networks for Unsupervised Domain Adaptationcited by 141
  22. 2018Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shiftcited by 109
  23. 2020CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistencycited by 107
  24. 2018Visual Domain Adaptation with Manifold Embedded Distribution Alignmentcited by 91
  25. 2017Partial Transfer Learning with Selective Adversarial Networkscited by 84
  26. 2019Unsupervised Domain Adaptation using Feature-Whitening and Consensus Losscited by 67
  27. 2020Towards Inheritable Models for Open-Set Domain Adaptationcited by 64
  28. 2018Multi-Source Domain Adaptation with Mixture of Expertscited by 62
  29. 2018AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimationcited by 54
  30. 2018Algorithms and Theory for Multiple-Source Adaptationcited by 53
  31. 2020Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Surveycited by 47
  32. 2018Co-regularized Alignment for Unsupervised Domain Adaptationcited by 39
  33. 2020Class-Incremental Domain Adaptationcited by 36
  34. 2019UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillationcited by 23
  35. 2017Knowledge Adaptation: Teaching to Adaptcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 9; 2023: 8; 2024: 7; 2025: 6; 2026: 1.

42 papers.

Sort:

By area:

  1. 2021Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentationcited by 81
  2. 2022A Broad Study of Pre-training for Domain Generalization and Adaptationcited by 64
  3. 2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
  4. 2022Balancing Discriminability and Transferability for Source-Free Domain Adaptationcited by 58
  5. 2021DINE: Domain Adaptation from Single and Multiple Black-box Predictorscited by 51
  6. 2022BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptationcited by 39
  7. 2021ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptationcited by 33
  8. 2024Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptationcited by 32
  9. 2022Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptationcited by 25
  10. 2022Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptationcited by 21
  11. 2021The First Vision For Vitals (V4V) Challenge for Non-Contact Video-Based Physiological Estimationcited by 19
  12. 2022SphereFed: Hyperspherical Federated Learningcited by 19
30 more
  1. 2023Domain-Specificity Inducing Transformers for Source-Free Domain Adaptationcited by 16
  2. 2022Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detectioncited by 14
  3. 2024LanDA: Language-Guided Multi-Source Domain Adaptationcited by 13
  4. 2021Secure Domain Adaptation with Multiple Sourcescited by 12
  5. 2021Multi-Source domain adaptation via supervised contrastive learning and confident consistency regularizationcited by 12
  6. 2023Subject-Based Domain Adaptation for Facial Expression Recognitioncited by 11
  7. 2021Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptationcited by 10
  8. 2023Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clusteringcited by 9
  9. 2024More is Better: Deep Domain Adaptation with Multiple Sourcescited by 9
  10. 2021Semi-Supervised Visual Representation Learning for Fashion Compatibilitycited by 8
  11. 2024Enhancing Domain Adaptation through Prompt Gradient Alignmentcited by 8
  12. 2021Multi-source Few-shot Domain Adaptationcited by 7
  13. 2025Progressive Multi-Source Domain Adaptation for Personalized Facial Expression Recognitioncited by 6
  14. 2022Self-Supervised Graph Neural Network for Multi-Source Domain Adaptationcited by 5
  15. 2025Preserving Clusters in Prompt Learning for Unsupervised Domain Adaptationcited by 4
  16. 2025MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Trainingcited by 4
  17. 2021Reciprocal Normalization for Domain Adaptationcited by 3
  18. 2023Relating tSNE and UMAP to Classical Dimensionality Reductioncited by 3
  19. 2025Vision-aware Multimodal Prompt Tuning for Uploadable Multi-source Few-shot Domain Adaptationcited by 3
  20. 2025Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentationcited by 3
  21. 2023MMRDN: Consistent Representation for Multi-View Manipulation Relationship Detection in Object-Stacked Scenescited by 1
  22. 2023FREEDOM: Target Label & Source Data & Domain Information-Free Multi-Source Domain Adaptation for Unsupervised Personalizationcited by 1
  23. 2023Adapt Anything: Tailor Any Image Classifiers across Domains And Categories Using Text-to-Image Diffusion Modelscited by 1
  24. 2024Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectorscited by 1
  25. 2022Joint Attention-Driven Domain Fusion and Noise-Tolerant Learning for Multi-Source Domain Adaptationcited by 0
  26. 2023Dynamic Domain Discrepancy Adjustment for Active Multi-Domain Adaptationcited by 0
  27. 2024Unsupervised Federated Domain Adaptation for Segmentation of MRI Imagescited by 0
  28. 2024Unveiling the Superior Paradigm: A Comparative Study of Source-Free Domain Adaptation and Unsupervised Domain Adaptationcited by 0
  29. 2025One-Shot Federated Unsupervised Domain Adaptation with Scaled Entropy Attention and Multi-Source Smoothed Pseudo Labelingcited by 0
  30. 2026Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controlscited by 0