mlsanityData to 7 Oct 2026

Maximum Classifier Discrepancy for Unsupervised Domain Adaptation

arXiv 1712.02560 ↗First posted 7 Dec 2017cs.CVcited by 682

Not on the map. Why?

Abstract (arXiv)

In this work, we present a method for unsupervised domain adaptation. Many adversarial learning methods train domain classifier networks to distinguish the features as either a source or target and train a feature generator network to mimic the discriminator. Two problems exist with these methods. First, the domain classifier only tries to distinguish the features as a source or target and thus does not consider task-specific decision boundaries between classes. Therefore, a trained generator can generate ambiguous features near class boundaries. Second, these methods aim to completely match the feature distributions between different domains, which is difficult because of each domain's characteristics. To solve these problems, we introduce a new approach that attempts to align distributions of source and target by utilizing the task-specific decision boundaries. We propose to maximize the discrepancy between two classifiers' outputs to detect target samples that are far from the support of the source. A feature generator learns to generate target features near the support to minimize the discrepancy. Our method outperforms other methods on several datasets of image classification and semantic segmentation. The codes are available at urlhttps://github.com/mil-tokyo/MCDDA

Key facts. Cited by 682 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 208; 2022: 152; 2023: 141; 2024: 95; 2025: 54; 2026: 32.

682 papers.

Sort:

By area:

  1. 2021Domain Generalization: A Surveycited by 760
  2. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  3. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
  4. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  5. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  6. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
  7. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  8. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 176
  9. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 176
  10. 2021Generalized Source-free Domain Adaptationcited by 175
  11. 2024Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Searchcited by 171
  12. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 163
38 more
  1. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 158
  2. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  3. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
  4. 2022Domain Adaptation via Prompt Learningcited by 128
  5. 2023Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behaviorcited by 128
  6. 2021Cycle Self-Training for Domain Adaptationcited by 120
  7. 2021Deep Subdomain Adaptation Network for Image Classificationcited by 119
  8. 2021Source-free Domain Adaptation via Avatar Prototype Generation and Adaptationcited by 111
  9. 2021MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detectioncited by 106
  10. 2021AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptationcited by 104
  11. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  12. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  13. 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
  14. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
  15. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 93
  16. 2021Domain Impression: A Source Data Free Domain Adaptation Methodcited by 91
  17. 2021Extending the WILDS Benchmark for Unsupervised Adaptationcited by 85
  18. 2022A Closer Look at Smoothness in Domain Adversarial Trainingcited by 85
  19. 2023DataDAM: Efficient Dataset Distillation with Attention Matchingcited by 83
  20. 2021TVT: Transferable Vision Transformer for Unsupervised Domain Adaptationcited by 81
  21. 2021Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentationcited by 81
  22. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
  23. 2022Semantic-Aware Domain Generalized Segmentationcited by 78
  24. 2021Unsupervised Multi-source Domain Adaptation Without Access to Source Datacited by 76
  25. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  26. 2021Cross-domain Contrastive Learning for Unsupervised Domain Adaptationcited by 75
  27. 2024Test-Time Model Adaptation with Only Forward Passescited by 74
  28. 2021VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptationcited by 69
  29. 2022Agree to Disagree: Diversity through Disagreement for Better Transferabilitycited by 69
  30. 2021Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptationcited by 67
  31. 2021Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptationcited by 67
  32. 2022Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypescited by 67
  33. 2022Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptationcited by 66
  34. 2021Category Contrast for Unsupervised Domain Adaptation in Visual Taskscited by 65
  35. 2021MixStyle Neural Networks for Domain Generalization and Adaptationcited by 64
  36. 2022A Broad Study of Pre-training for Domain Generalization and Adaptationcited by 64
  37. 2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
  38. 2023AD-CLIP: Adapting Domains in Prompt Space Using CLIPcited by 62

50 most cited of 682 All 682 (JSON)