mlsanityData to 7 Oct 2026

Towards Unified and Effective Domain Generalization

arXiv 2310.10008 ↗First posted 16 Oct 2023cs.CV cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

We propose UniDG, a novel and Unified framework for Domain Generalization that is capable of significantly enhancing the out-of-distribution generalization performance of foundation models regardless of their architectures. The core idea of UniDG is to finetune models during the inference stage, which saves the cost of iterative training. Specifically, we encourage models to learn the distribution of test data in an unsupervised manner and impose a penalty regarding the updating step of model parameters. The penalty term can effectively reduce the catastrophic forgetting issue as we would like to maximally preserve the valuable knowledge in the original model. Empirically, across 12 visual backbones, including CNN-, MLP-, and Transformer-based models, ranging from 1.89M to 303M parameters, UniDG shows an average accuracy improvement of +5.4% on DomainBed. These performance results demonstrate the superiority and versatility of UniDG. The code is publicly available at https://github.com/invictus717/UniDG

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 74 of its 96 references that are in the map. First posted on arXiv 16 Oct 2023.

Builds on

74 of 96 references.

References · 74

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  10. 2022A ConvNet for the 2020scited by 3,545
  11. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  12. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
38 more
  1. 2016Learning without Forgettingcited by 2,465
  2. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  3. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  4. 2019Searching for MobileNetV3cited by 1,984
  5. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  6. 2019Invariant Risk Minimizationcited by 1,832
  7. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  8. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  9. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  10. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  11. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  12. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  13. 2020In Search of Lost Domain Generalizationcited by 1,042
  14. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  15. 2020Designing Network Design Spacescited by 954
  16. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  17. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  18. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  19. 2021Domain Generalization: A Surveycited by 760
  20. 2018Recognition in Terra Incognitacited by 655
  21. 2021Domain Generalization with MixStylecited by 563
  22. 2022Continual Test-Time Domain Adaptationcited by 520
  23. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  24. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
  25. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  26. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  27. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 285
  28. 2021Gradient Matching for Domain Generalizationcited by 258
  29. 2022Contrastive Test-Time Adaptationcited by 258
  30. 2019Episodic Training for Domain Generalizationcited by 245
  31. 2020Domain Generalization using Causal Matchingcited by 224
  32. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  33. 2020Universal Domain Adaptation through Self Supervisioncited by 172
  34. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  35. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
  36. 2020Adversarial Continual Learningcited by 140
  37. 2020Efficient Domain Generalization via Common-Specific Low-Rank Decompositioncited by 134
  38. 2022Domain Generalization by Mutual-Information Regularization with Pre-trained Modelscited by 133

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

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

5 papers.

  1. 2025Visual RAG: Expanding MLLM visual knowledge without fine-tuningcited by 11
  2. 2024FunOTTA: On-the-Fly Adaptation on Cross-Domain Fundus Image via Stable Test-time Trainingcited by 3
  3. 2025VeLU: Variance-enhanced Learning Unit for Deep Neural Networkscited by 1
  4. 2026Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptationcited by 1
  5. 2025Target-Oriented Single Domain Generalizationcited by 0