mlsanityData to 7 Oct 2026

Learning Transferable Features with Deep Adaptation Networks

arXiv 1502.02791 ↗First posted 10 Feb 2015cs.LGcited by 1,323

Not on the map. Why?

Abstract (arXiv)

Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the feature transferability drops significantly in higher layers with increasing domain discrepancy. Hence, it is important to formally reduce the dataset bias and enhance the transferability in task-specific layers. In this paper, we propose a new Deep Adaptation Network (DAN) architecture, which generalizes deep convolutional neural network to the domain adaptation scenario. In DAN, hidden representations of all task-specific layers are embedded in a reproducing kernel Hilbert space where the mean embeddings of different domain distributions can be explicitly matched. The domain discrepancy is further reduced using an optimal multi-kernel selection method for mean embedding matching. DAN can learn transferable features with statistical guarantees, and can scale linearly by unbiased estimate of kernel embedding. Extensive empirical evidence shows that the proposed architecture yields state-of-the-art image classification error rates on standard domain adaptation benchmarks.

Key facts. Cited by 1,323 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Feb 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 333; 2022: 292; 2023: 261; 2024: 184; 2025: 146; 2026: 106.

1,323 papers.

Sort:

By area:

  1. 2021Domain Generalization: A Surveycited by 760
  2. 2022Continual Test-Time Domain Adaptationcited by 520
  3. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  4. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  5. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 259
  6. 2022Contrastive Test-Time Adaptationcited by 258
  7. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  8. 2022Test-Time Training with Masked Autoencoderscited by 208
  9. 2021Trustworthy AI: From Principles to Practicescited by 206
  10. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  11. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  12. 2022Parameter-free Online Test-time Adaptationcited by 184
38 more
  1. 2019Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Modelscited by 177
  2. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 176
  3. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 176
  4. 2021Generalized Source-free Domain Adaptationcited by 175
  5. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  6. 2021Learning to Diversify for Single Domain Generalizationcited by 170
  7. 2021LogME: Practical Assessment of Pre-trained Models for Transfer Learningcited by 168
  8. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 158
  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. 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
  12. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
  13. 2022Domain Adaptation via Prompt Learningcited by 128
  14. 2021Cross-Domain Adaptive Teacher for Object Detectioncited by 125
  15. 2021Cycle Self-Training for Domain Adaptationcited by 120
  16. 2021Deep Subdomain Adaptation Network for Image Classificationcited by 119
  17. 2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
  18. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  19. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  20. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  21. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  22. 2022Source-Free Domain Adaptation via Distribution Estimationcited by 97
  23. 2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
  24. 2021Progressive Domain Expansion Network for Single Domain Generalizationcited by 96
  25. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
  26. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 93
  27. 2021OVANet: One-vs-All Network for Universal Domain Adaptationcited by 92
  28. 2021Towards Principled Disentanglement for Domain Generalizationcited by 91
  29. 2021Invariant Information Bottleneck for Domain Generalizationcited by 86
  30. 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 86
  31. 2021Delving Deep into the Generalization of Vision Transformers under Distribution Shiftscited by 85
  32. 2021Extending the WILDS Benchmark for Unsupervised Adaptationcited by 85
  33. 2022Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Timecited by 85
  34. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  35. 2023When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directionscited by 83
  36. 2021TVT: Transferable Vision Transformer for Unsupervised Domain Adaptationcited by 81
  37. 2021Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learningcited by 78
  38. 2022Semantic-Aware Domain Generalized Segmentationcited by 78

50 most cited of 1,323 All 1,323 (JSON)