mlsanityData to 14 Oct 2026

Domain Adaptation via Feature Refinement

arXiv 2508.16124 ↗First posted 22 Aug 2025cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose Domain Adaptation via Feature Refinement (DAFR2), a simple yet effective framework for unsupervised domain adaptation under distribution shift. The proposed method synergistically combines three key components: adaptation of Batch Normalization statistics using unlabeled target data, feature distillation from a source-trained model and hypothesis transfer. By aligning feature distributions at the statistical and representational levels, DAFR2 produces robust and domain-invariant feature spaces that generalize across similar domains without requiring target labels, complex architectures or sophisticated training objectives. Extensive experiments on benchmark datasets, including CIFAR10-C, CIFAR100-C, MNIST-C and PatchCamelyon-C, demonstrate that the proposed algorithm outperforms prior methods in robustness to corruption. Theoretical and empirical analyses further reveal that our method achieves improved feature alignment, increased mutual information between the domains and reduced sensitivity to input perturbations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 77 of its 103 references that are in the map. First posted on arXiv 22 Aug 2025.

Builds on

77 of 103 references.

References · 77

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2017On Calibration of Modern Neural Networkscited by 4,960
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  7. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  8. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  9. 2016Wide Residual Networkscited by 3,070
  10. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  11. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  12. 2020Exploring Simple Siamese Representation Learningcited by 2,866
38 more
  1. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  2. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  3. 2014FitNets: Hints for Thin Deep Netscited by 1,653
  4. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
  5. 2019Natural Adversarial Examplescited by 1,408
  6. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  7. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  8. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,077
  9. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  10. 2015Deep Learning and the Information Bottleneck Principlecited by 802
  11. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  12. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
  13. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  14. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 612
  15. 2022Continual Test-Time Domain Adaptationcited by 525
  16. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
  17. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 454
  18. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 431
  19. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 415
  20. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  21. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 377
  22. 2016Kernel Mean Embedding of Distributions: A Review and Beyondcited by 364
  23. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  24. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  25. 2016Domain Separation Networkscited by 320
  26. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 308
  27. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  28. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 288
  29. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 288
  30. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 249
  31. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 236
  32. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 210
  33. 2018Multi-Adversarial Domain Adaptationcited by 196
  34. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 189
  35. 2020Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfercited by 173
  36. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 164
  37. 2017Asymmetric Tri-training for Unsupervised Domain Adaptationcited by 152
  38. 2019MNIST-C: A Robustness Benchmark for Computer Visioncited by 138

50 most cited of 77 All 77 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
  2. 2025Noise Optimized Conditional Diffusion for Domain Adaptation
  3. 2022Domain Adaptation via Prompt Learning
  4. 2024Enhancing Domain Adaptation through Prompt Gradient Alignment
  5. 2024Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank
  6. 2026DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation
  7. 2025Reinforced Domain Selection for Continuous Domain Adaptation
  8. 2025Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation