mlsanityData to 7 Oct 2026

Open-Set Multi-Source Multi-Target Domain Adaptation

arXiv 2302.00995 ↗First posted 2 Feb 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Single-Source Single-Target Domain Adaptation (1S1T) aims to bridge the gap between a labelled source domain and an unlabelled target domain. Despite 1S1T being a well-researched topic, they are typically not deployed to the real world. Methods like Multi-Source Domain Adaptation and Multi-Target Domain Adaptation have evolved to model real-world problems but still do not generalise well. The fact that most of these methods assume a common label-set between source and target is very restrictive. Recent Open-Set Domain Adaptation methods handle unknown target labels but fail to generalise in multiple domains. To overcome these difficulties, first, we propose a novel generic domain adaptation (DA) setting named Open-Set Multi-Source Multi-Target Domain Adaptation (OS-nSmT), with n and m being number of source and target domains respectively. Next, we propose a graph attention based framework named DEGAA which can capture information from multiple source and target domains without knowing the exact label-set of the target. We argue that our method, though offered for multiple sources and multiple targets, can also be agnostic to various other DA settings. To check the robustness and versatility of DEGAA, we put forward ample experiments and ablation studies.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 54 of its 74 references that are in the map. First posted on arXiv 2 Feb 2023.

Builds on

54 of 74 references.

References · 54

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  7. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  8. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  9. 2019Invariant Risk Minimizationcited by 1,832
  10. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  11. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  12. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
38 more
  1. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  2. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  3. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  4. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  5. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  6. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  7. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  8. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  9. 2015Towards Open Set Deep Networkscited by 533
  10. 2020What is being transferred in transfer learning?cited by 365
  11. 2016Kernel Mean Embedding of Distributions: A Review and Beyondcited by 360
  12. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  13. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  14. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  15. 2019Adversarial Domain Adaptation with Domain Mixupcited by 250
  16. 2020Domain Generalization using Causal Matchingcited by 224
  17. 2017Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learningcited by 192
  18. 2020Improve Unsupervised Domain Adaptation with Mixup Trainingcited by 185
  19. 2017Generate To Adapt: Aligning Domains using Generative Adversarial Networkscited by 183
  20. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  21. 2017Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptationcited by 151
  22. 2018Open Set Domain Adaptation by Backpropagationcited by 150
  23. 2018Domain Generalization via Conditional Invariant Representationcited by 146
  24. 2020Gradually Vanishing Bridge for Adversarial Domain Adaptationcited by 130
  25. 2020FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptationcited by 124
  26. 2018Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shiftcited by 109
  27. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  28. 2019Domain Agnostic Learning with Disentangled Representationscited by 107
  29. 2020Heterogeneous Domain Generalization via Domain Mixupcited by 103
  30. 2021Adaptive Methods for Real-World Domain Generalizationcited by 66
  31. 2020Progressive Graph Learning for Open-Set Domain Adaptationcited by 56
  32. 2017Adversarial Feature Augmentation for Unsupervised Domain Adaptationcited by 48
  33. 2020Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Surveycited by 47
  34. 2020Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillationcited by 46
  35. 2021Multi-Target Domain Adaptation with Collaborative Consistency Learningcited by 43
  36. 2018Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximizationcited by 40
  37. 2018Multi-component Image Translation for Deep Domain Generalizationcited by 40
  38. 2019Blending-target Domain Adaptation by Adversarial Meta-Adaptation Networkscited by 37

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Improving Domain Adaptation Through Class Aware Frequency Transformationcited by 1