mlsanityData to 14 Oct 2026

Order-preserving Consistency Regularization for Domain Adaptation and Generalization

arXiv 2309.13258 ↗First posted 23 Sep 2023cs.CV cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Deep learning models fail on cross-domain challenges if the model is oversensitive to domain-specific attributes, e.g., lightning, background, camera angle, etc. To alleviate this problem, data augmentation coupled with consistency regularization are commonly adopted to make the model less sensitive to domain-specific attributes. Consistency regularization enforces the model to output the same representation or prediction for two views of one image. These constraints, however, are either too strict or not order-preserving for the classification probabilities. In this work, we propose the Order-preserving Consistency Regularization (OCR) for cross-domain tasks. The order-preserving property for the prediction makes the model robust to task-irrelevant transformations. As a result, the model becomes less sensitive to the domain-specific attributes. The comprehensive experiments show that our method achieves clear advantages on five different cross-domain tasks.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 61 of its 83 references that are in the map. First posted on arXiv 23 Sep 2023.

Builds on

61 of 83 references.

References · 61

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  8. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  9. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  10. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  11. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  12. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
38 more
  1. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  2. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  3. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  4. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  5. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  6. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  7. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  8. 2014How transferable are features in deep neural networks?cited by 1,225
  9. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  10. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  11. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  12. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  13. 2016Adversarial Machine Learning at Scalecited by 936
  14. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  15. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  16. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  17. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
  18. 2013Domain Generalization via Invariant Feature Representationcited by 623
  19. 2021Domain Generalization with MixStylecited by 566
  20. 2022Continual Test-Time Domain Adaptationcited by 525
  21. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
  22. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  23. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 434
  24. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 403
  25. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 364
  26. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 352
  27. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 323
  28. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  29. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 288
  30. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  31. 2018DropBlock: A regularization method for convolutional networkscited by 262
  32. 2022Contrastive Test-Time Adaptationcited by 261
  33. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  34. 2014Learning with Pseudo-Ensemblescited by 241
  35. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 215
  36. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 215
  37. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  38. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 177

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 5; 2026: 3.

11 papers.

  1. 2023Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentationcited by 83
  2. 2024SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learningcited by 24
  3. 2024Adapting Fine-Grained Cross-View Localization to Areas without Fine Ground Truthcited by 14
  4. 2025Single-Domain Generalized Object Detection by Balancing Domain Diversity and Invariancecited by 2
  5. 2025Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Modelscited by 2
  6. 2025Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentationcited by 1
  7. 2025IELDG: Suppressing Domain-Specific Noise with Inverse Evolution Layers for Domain Generalized Semantic Segmentationcited by 0
  8. 2025Dropout Prompt Learning: Towards Robust and Adaptive Vision-Language Modelscited by 0
  9. 2026DDS-UDA: Dual-Domain Synergy for Unsupervised Domain Adaptation in Joint Segmentation of Optic Disc and Optic Cupcited by 0
  10. 2026CRISP: Rank-Guided Iterative Squeezing for Robust Medical Image Segmentation under Domain Shiftcited by 0
  11. 2026CRISP: Constrained Refinement via Iterative Squeezing Process for Robust Medical Image Segmentation under Domain Shiftcited by 0