mlsanityData to 7 Oct 2026

Adversarial Discriminative Domain Adaptation

arXiv 1702.05464 ↗First posted 17 Feb 2017cs.CVcited by 1,309

Not on the map. Why?

Abstract (arXiv)

Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several adversarial approaches to unsupervised domain adaptation have recently been introduced, which reduce the difference between the training and test domain distributions and thus improve generalization performance. Prior generative approaches show compelling visualizations, but are not optimal on discriminative tasks and can be limited to smaller shifts. Prior discriminative approaches could handle larger domain shifts, but imposed tied weights on the model and did not exploit a GAN-based loss. We first outline a novel generalized framework for adversarial adaptation, which subsumes recent state-of-the-art approaches as special cases, and we use this generalized view to better relate the prior approaches. We propose a previously unexplored instance of our general framework which combines discriminative modeling, untied weight sharing, and a GAN loss, which we call Adversarial Discriminative Domain Adaptation (ADDA). We show that ADDA is more effective yet considerably simpler than competing domain-adversarial methods, and demonstrate the promise of our approach by exceeding state-of-the-art unsupervised adaptation results on standard cross-domain digit classification tasks and a new more difficult cross-modality object classification task.

Key facts. Cited by 1,309 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 3; 2021: 349; 2022: 313; 2023: 261; 2024: 170; 2025: 149; 2026: 64.

1,309 papers.

Sort:

By area:

  1. 2021Domain Generalization: A Surveycited by 760
  2. 2021Deep Long-Tailed Learning: A Surveycited by 416
  3. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  4. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  5. 2022Contrastive Test-Time Adaptationcited by 258
  6. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  7. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 176
  8. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 163
  9. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  10. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  11. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 140
  12. 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
38 more
  1. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
  2. 2021Cross-Domain Adaptive Teacher for Object Detectioncited by 125
  3. 2022Causal Transformer for Estimating Counterfactual Outcomescited by 121
  4. 2021Cycle Self-Training for Domain Adaptationcited by 120
  5. 2021AdaRNN: Adaptive Learning and Forecasting of Time Seriescited by 120
  6. 2021Deep Subdomain Adaptation Network for Image Classificationcited by 119
  7. 2021Predicting with Confidence on Unseen Distributionscited by 116
  8. 2021Source-free Domain Adaptation via Avatar Prototype Generation and Adaptationcited by 111
  9. 2021Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identificationcited by 108
  10. 2021MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detectioncited by 106
  11. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  12. 2021Model-Based Domain Generalizationcited by 103
  13. 2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 102
  14. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 99
  15. 2022Clothes-Changing Person Re-identification with RGB Modality Onlycited by 98
  16. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  17. 2022Source-Free Domain Adaptation via Distribution Estimationcited by 97
  18. 2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
  19. 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
  20. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
  21. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 93
  22. 2021OVANet: One-vs-All Network for Universal Domain Adaptationcited by 92
  23. 2021Domain Impression: A Source Data Free Domain Adaptation Methodcited by 91
  24. 2021Learned Coarse Models for Efficient Turbulence Simulationcited by 90
  25. 2022SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentationcited by 87
  26. 2021Invariant Information Bottleneck for Domain Generalizationcited by 86
  27. 2021Adversarially Adaptive Normalization for Single Domain Generalizationcited by 85
  28. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 84
  29. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  30. 2021TVT: Transferable Vision Transformer for Unsupervised Domain Adaptationcited by 81
  31. 2021Causal Attention for Unbiased Visual Recognitioncited by 80
  32. 2022Semantic-Aware Domain Generalized Segmentationcited by 78
  33. 2022Deep Clustering: A Comprehensive Surveycited by 78
  34. 2021Unsupervised Multi-source Domain Adaptation Without Access to Source Datacited by 76
  35. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  36. 2021Cross-domain Contrastive Learning for Unsupervised Domain Adaptationcited by 75
  37. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  38. 2023Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Taskscited by 72

50 most cited of 1,309 All 1,309 (JSON)