mlsanityData to 14 Oct 2026

Compound Domain Generalization via Meta-Knowledge Encoding

arXiv 2203.13006 ↗First posted 24 Mar 2022cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

Domain generalization (DG) aims to improve the generalization performance for an unseen target domain by using the knowledge of multiple seen source domains. Mainstream DG methods typically assume that the domain label of each source sample is known a priori, which is challenged to be satisfied in many real-world applications. In this paper, we study a practical problem of compound DG, which relaxes the discrete domain assumption to the mixed source domains setting. On the other hand, current DG algorithms prioritize the focus on semantic invariance across domains (one-vs-one), while paying less attention to the holistic semantic structure (many-vs-many). Such holistic semantic structure, referred to as meta-knowledge here, is crucial for learning generalizable representations. To this end, we present Compound Domain Generalization via Meta-Knowledge Encoding (COMEN), a general approach to automatically discover and model latent domains in two steps. Firstly, we introduce Style-induced Domain-specific Normalization (SDNorm) to re-normalize the multi-modal underlying distributions, thereby dividing the mixture of source domains into latent clusters. Secondly, we harness the prototype representations, the centroids of classes, to perform relational modeling in the embedding space with two parallel and complementary modules, which explicitly encode the semantic structure for the out-of-distribution generalization. Experiments on four standard DG benchmarks reveal that COMEN exceeds the state-of-the-art performance without the need of domain supervision.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). Builds on 47 of its 72 references that are in the map. First posted on arXiv 24 Mar 2022.

Builds on

47 of 72 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Graph Attention Networkscited by 8,923
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  7. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  9. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  10. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  11. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  12. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
35 more
  1. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  2. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  3. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
  4. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  5. 2013Domain Generalization via Invariant Feature Representationcited by 623
  6. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  7. 2021Domain Generalization with MixStylecited by 566
  8. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  9. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
  10. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  11. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 407
  12. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 323
  13. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  14. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 288
  15. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  16. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  17. 2019Episodic Training for Domain Generalizationcited by 245
  18. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  19. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  20. 2019Domain-Specific Batch Normalization for Unsupervised Domain Adaptationcited by 197
  21. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  22. 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
  23. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
  24. 2019Learning to Optimize Domain Specific Normalization for Domain Generalizationcited by 161
  25. 2020Robust and Generalizable Visual Representation Learning via Random Convolutionscited by 142
  26. 2020Efficient Domain Generalization via Common-Specific Low-Rank Decompositioncited by 134
  27. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  28. 2019Domain-Symmetric Networks for Adversarial Domain Adaptationcited by 120
  29. 2020Learning from Extrinsic and Intrinsic Supervisions for Domain Generalizationcited by 108
  30. 2017AutoDIAL: Automatic DomaIn Alignment Layerscited by 75
  31. 2020Towards Recognizing Unseen Categories in Unseen Domainscited by 56
  32. 2018Boosting Domain Adaptation by Discovering Latent Domainscited by 46
  33. 2020Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practicecited by 43
  34. 2020Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptationcited by 35
  35. 2021I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectorscited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 23; 2024: 8; 2025: 1; 2026: 2.

40 papers.

Sort:

By area:

  1. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  2. 2023Improved Test-Time Adaptation for Domain Generalizationcited by 47
  3. 2023ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalizationcited by 28
  4. 2023SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detectioncited by 28
  5. 2023Decompose, Adjust, Compose: Effective Normalization by Playing with Frequency for Domain Generalizationcited by 26
  6. 2022A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learningcited by 25
  7. 2023What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locationscited by 25
  8. 2023DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalizationcited by 21
  9. 2022Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalizationcited by 20
  10. 2023Domain Generalization via Rationale Invariancecited by 16
  11. 2023Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issuescited by 12
  12. 2023Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive Learningcited by 11
28 more
  1. 2023Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalizationcited by 11
  2. 2023PVG: Progressive Vision Graph for Vision Recognitioncited by 10
  3. 2023Activate and Reject: Towards Safe Domain Generalization under Category Shiftcited by 9
  4. 2022HMOE: Hypernetwork-based Mixture of Experts for Domain Generalizationcited by 8
  5. 2023Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalizationcited by 8
  6. 2023NormAUG: Normalization-guided Augmentation for Domain Generalizationcited by 8
  7. 2023Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentationcited by 8
  8. 2024LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalizationcited by 8
  9. 2023Generalizing to Unseen Domains in Diabetic Retinopathy Classificationcited by 7
  10. 2024Adaptive Prediction Ensemble: Improving Out-of-Distribution Generalization of Motion Forecastingcited by 7
  11. 2023MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learningcited by 6
  12. 2022A Comprehensive Review of Trends, Applications and Challenges In Out-of-Distribution Detectioncited by 5
  13. 2023Towards Unified and Effective Domain Generalizationcited by 5
  14. 2024Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlationscited by 5
  15. 2022Gated Domain Units for Multi-source Domain Generalizationcited by 4
  16. 2024A Causal Inspired Early-Branching Structure for Domain Generalizationcited by 4
  17. 2024Feature Diversification and Adaptation for Federated Domain Generalizationcited by 4
  18. 2024START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformationcited by 4
  19. 2023Unsupervised Adaptation of Polyp Segmentation Models via Coarse-to-Fine Self-Supervisioncited by 2
  20. 2023DoubleAUG: Single-domain Generalized Object Detector in Urban via Color Perturbation and Dual-style Memorycited by 2
  21. 2024Learning in Order! A Sequential Strategy to Learn Invariant Features for Multimodal Sentiment Analysiscited by 2
  22. 2025Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalizationcited by 2
  23. 2023Domain Generalization Deep Graph Transformationcited by 1
  24. 2023Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic Segmentationcited by 1
  25. 2023Parameter Exchange for Robust Dynamic Domain Generalizationcited by 1
  26. 2026Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysiscited by 1
  27. 2024Mixstyle-Entropy: Domain Generalization with Causal Intervention and Perturbationcited by 0
  28. 2026CLARE: Scalable Class-Incremental Continual Learning via a Sparsity-Based Frameworkcited by 0