mlsanityData to 14 Oct 2026

Domain-Adversarial Training of Neural Networks

arXiv 1505.07818 ↗First posted 28 May 2015stat.ML cs.LG cs.NEcited by 3,044

Not on the map. Why?

Cited by 36 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains. The approach implements this idea in the context of neural network architectures that are trained on labeled data from the source domain and unlabeled data from the target domain (no labeled target-domain data is necessary). As the training progresses, the approach promotes the emergence of features that are (i) discriminative for the main learning task on the source domain and (ii) indiscriminate with respect to the shift between the domains. We show that this adaptation behaviour can be achieved in almost any feed-forward model by augmenting it with few standard layers and a new gradient reversal layer. The resulting augmented architecture can be trained using standard backpropagation and stochastic gradient descent, and can thus be implemented with little effort using any of the deep learning packages. We demonstrate the success of our approach for two distinct classification problems (document sentiment analysis and image classification), where state-of-the-art domain adaptation performance on standard benchmarks is achieved. We also validate the approach for descriptor learning task in the context of person re-identification application.

Key facts. Cited by 3,044 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 May 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 3; 2020: 1; 2021: 540; 2022: 601; 2023: 590; 2024: 461; 2025: 420; 2026: 427.

3,044 papers.

Sort:

By area:

  1. 2024Depth Anything V2cited by 1,422
  2. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  3. 2021Domain Generalization: A Surveycited by 764
  4. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  5. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 434
  6. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 381
  7. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 356
  8. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 352
  9. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
  10. 2022Contrastive Test-Time Adaptationcited by 261
  11. 2021Gradient Matching for Domain Generalizationcited by 258
  12. 2021SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retrainingcited by 237
38 more
  1. 2024Continual Learning of Large Language Models: A Comprehensive Surveycited by 234
  2. 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
  3. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 215
  4. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  5. 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
  6. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  7. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 189
  8. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  9. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 178
  10. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 177
  11. 2021Generalized Source-free Domain Adaptationcited by 175
  12. 2022Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlationscited by 172
  13. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  14. 2021Learning to Diversify for Single Domain Generalizationcited by 170
  15. 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
  16. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 164
  17. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  18. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  19. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  20. 2021Unsupervised Speech Recognitioncited by 148
  21. 2022Diverse Weight Averaging for Out-of-Distribution Generalizationcited by 148
  22. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  23. 2021Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalizationcited by 144
  24. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  25. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 141
  26. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 139
  27. 2022Domain Generalization by Mutual-Information Regularization with Pre-trained Modelscited by 133
  28. 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
  29. 2023Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behaviorcited by 131
  30. 2021Cross-Domain Adaptive Teacher for Object Detectioncited by 126
  31. 2021Unbalanced minibatch Optimal Transport; applications to Domain Adaptationcited by 125
  32. 2021AdaRNN: Adaptive Learning and Forecasting of Time Seriescited by 121
  33. 2021Cycle Self-Training for Domain Adaptationcited by 120
  34. 2021Deep Subdomain Adaptation Network for Image Classificationcited by 119
  35. 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
  36. 2021Predicting with Confidence on Unseen Distributionscited by 116
  37. 2021Source-free Domain Adaptation via Avatar Prototype Generation and Adaptationcited by 111
  38. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107

50 most cited of 3,044 All 3,044 (JSON)