mlsanityData to 7 Oct 2026

Uncertainty-guided Model Generalization to Unseen Domains

arXiv 2103.07531 ↗First posted 12 Mar 2021cs.CVcited by 41

Not on the map. Why?

Abstract (arXiv)

We study a worst-case scenario in generalization: Out-of-domain generalization from a single source. The goal is to learn a robust model from a single source and expect it to generalize over many unknown distributions. This challenging problem has been seldom investigated while existing solutions suffer from various limitations. In this paper, we propose a new solution. The key idea is to augment the source capacity in both input and label spaces, while the augmentation is guided by uncertainty assessment. To the best of our knowledge, this is the first work to (1) access the generalization uncertainty from a single source and (2) leverage it to guide both input and label augmentation for robust generalization. The model training and deployment are effectively organized in a Bayesian meta-learning framework. We conduct extensive comparisons and ablation study to validate our approach. The results prove our superior performance in a wide scope of tasks including image classification, semantic segmentation, text classification, and speech recognition.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 46 of its 68 references that are in the map. First posted on arXiv 12 Mar 2021.

Builds on

46 of 68 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2013Intriguing properties of neural networkscited by 5,114
  9. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  10. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  11. 2016Wide Residual Networkscited by 3,057
  12. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
34 more
  1. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  2. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  3. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  4. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  5. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  6. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  7. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 741
  8. 2013Domain Generalization via Invariant Feature Representationcited by 622
  9. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 541
  10. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  11. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  12. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  13. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  14. 2017Wasserstein Auto-Encoderscited by 371
  15. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
  16. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
  17. 2020Learning to Learn Single Domain Generalizationcited by 295
  18. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  19. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  20. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  21. 2021SMIL: Multimodal Learning with Severely Missing Modalitycited by 243
  22. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  23. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
  24. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  25. 2017Image to Image Translation for Domain Adaptationcited by 171
  26. 2018Disentangling Adversarial Robustness and Generalizationcited by 171
  27. 2020Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustnesscited by 121
  28. 2017Few-Shot Adversarial Domain Adaptationcited by 111
  29. 2020Learning from Extrinsic and Intrinsic Supervisions for Domain Generalizationcited by 108
  30. 2017From source to target and back: symmetric bi-directional adaptive GANcited by 53
  31. 2019Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Taskscited by 48
  32. 2018Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimationcited by 44
  33. 2019d-SNE: Domain Adaptation using Stochastic Neighborhood Embeddingcited by 40
  34. 2019Addressing Model Vulnerability to Distributional Shifts over Image Transformation Setscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 4; 2023: 11; 2024: 10; 2025: 8; 2026: 3.

41 papers.

Sort:

By area:

  1. 2021Mutual Consistency Learning for Semi-supervised Medical Image Segmentationcited by 107
  2. 2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 69
  3. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 49
  4. 2021Semi-Supervised Domain Generalization with Stochastic StyleMatchcited by 43
  5. 2021Feature Stylization and Domain-aware Contrastive Learning for Domain Generalizationcited by 40
  6. 2022Attention Consistency on Visual Corruptions for Single-Source Domain Generalizationcited by 37
  7. 2021Feature-based Style Randomization for Domain Generalizationcited by 34
  8. 2021Transformer-Based Source-Free Domain Adaptationcited by 30
  9. 2024Domain Generalization through Meta-Learning: A Surveycited by 28
  10. 2022Domain Generalization via Frequency-domain-based Feature Disentanglement and Interactioncited by 21
  11. 2022AADG: Automatic Augmentation for Domain Generalization on Retinal Image Segmentationcited by 18
  12. 2023Are Data-driven Explanations Robust against Out-of-distribution Data?cited by 14
29 more
  1. 2024Uncertainty-guided Contrastive Learning for Single Source Domain Generalisationcited by 14
  2. 2023Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issuescited by 12
  3. 2023Topology-aware Robust Optimization for Out-of-distribution Generalizationcited by 7
  4. 2024Cross-Domain Feature Augmentation for Domain Generalizationcited by 7
  5. 2025Lightweight Medical Image Restoration via Integrating Reliable Lesion-Semantic Driven Priorcited by 7
  6. 2023Data Optimization in Deep Learning: A Surveycited by 6
  7. 2023C-SAW: Self-Supervised Prompt Learning for Image Generalization in Remote Sensingcited by 6
  8. 2024What Does Softmax Probability Tell Us about Classifiers Ranking Across Diverse Test Conditions?cited by 6
  9. 2023INSURE: An Information Theory Inspired Disentanglement and Purification Model for Domain Generalizationcited by 4
  10. 2024RaffeSDG: Random Frequency Filtering enabled Single-source Domain Generalization for Medical Image Segmentationcited by 3
  11. 2025Uncertainty-Instructed Structure Injection for Generalizable HD Map Constructioncited by 3
  12. 2025Towards Unveiling Predictive Uncertainty Vulnerabilities in the Context of the Right to Be Forgottencited by 3
  13. 2024Domain Adversarial Active Learning for Domain Generalization Classificationcited by 2
  14. 2024Domain Generalizable Person Search Using Unreal Datasetcited by 2
  15. 2024ED-SAM: An Efficient Diffusion Sampling Approach to Domain Generalization in Vision-Language Foundation Modelscited by 2
  16. 2025Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptationcited by 2
  17. 2025FrogDogNet: Fourier frequency Retained visual prompt Output Guidance for Domain Generalization of CLIP in Remote Sensingcited by 2
  18. 2023Trustworthy Representation Learning Across Domainscited by 1
  19. 2023Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic Segmentationcited by 1
  20. 2023Bayesian Domain Invariant Learning via Posterior Generalization of Parameter Distributionscited by 1
  21. 2024Adaptive Cascading Network for Continual Test-Time Adaptationcited by 1
  22. 2024Boosting Unconstrained Face Recognition with Targeted Style Adversarycited by 1
  23. 2025Pseudo Multi-Source Domain Generalization: Bridging the Gap Between Single and Multi-Source Domain Generalizationcited by 1
  24. 2026Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learningcited by 1
  25. 2023Frequency Decomposition to Tap the Potential of Single Domain for Generalizationcited by 0
  26. 2025ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extractioncited by 0
  27. 2025Lightweight Transformer Framework for Weakly Supervised Semantic Segmentationcited by 0
  28. 2026SemAlign: Language Guided Semi-supervised Domain Generalizationcited by 0
  29. 2026SAGE: Surrogate-gradient Adaptation via Attention-Guided Entropy for Spiking Transformerscited by 0