mlsanityData to 14 Oct 2026

DGFamba: Learning Flow Factorized State Space for Visual Domain Generalization

arXiv 2504.08019 ↗First posted 10 Apr 2025cs.CV cs.AIcited by 1

On the map: State-space sequence models (S4, Mamba) → Vision Mamba backbones

Abstract (arXiv)

Domain generalization aims to learn a representation from the source domain, which can be generalized to arbitrary unseen target domains. A fundamental challenge for visual domain generalization is the domain gap caused by the dramatic style variation whereas the image content is stable. The realm of selective state space, exemplified by VMamba, demonstrates its global receptive field in representing the content. However, the way exploiting the domain-invariant property for selective state space is rarely explored. In this paper, we propose a novel Flow Factorized State Space model, dubbed as DG-Famba, for visual domain generalization. To maintain domain consistency, we innovatively map the style-augmented and the original state embeddings by flow factorization. In this latent flow space, each state embedding from a certain style is specified by a latent probability path. By aligning these probability paths in the latent space, the state embeddings are able to represent the same content distribution regardless of the style differences. Extensive experiments conducted on various visual domain generalization settings show its state-of-the-art performance.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 32 of its 49 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

32 of 49 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  5. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  6. 2020In Search of Lost Domain Generalizationcited by 1,054
  7. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  8. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  9. 2021Domain Generalization with MixStylecited by 566
  10. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 434
  11. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  12. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 407
20 more
  1. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 328
  2. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  3. 2021A Fourier-based Framework for Domain Generalizationcited by 290
  4. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  5. 2021Partial success in closing the gap between human and machine visioncited by 185
  6. 2017Domain Generalization by Marginal Transfer Learningcited by 180
  7. 2020Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identificationcited by 110
  8. 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
  9. 2020Rethinking Importance Weighting for Deep Learning under Distribution Shiftcited by 93
  10. 2021Delving Deep into the Generalization of Vision Transformers under Distribution Shiftscited by 85
  11. 2022Sparse Mixture-of-Experts are Domain Generalizable Learnerscited by 85
  12. 2021MixStyle Neural Networks for Domain Generalization and Adaptationcited by 64
  13. 2022Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesiscited by 55
  14. 2022Self-Distilled Vision Transformer for Domain Generalizationcited by 35
  15. 2024Rethinking Multi-domain Generalization with A General Learning Objectivecited by 23
  16. 2024Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentationcited by 22
  17. 2022Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalizationcited by 20
  18. 2023Masked Images Are Counterfactual Samples for Robust Fine-tuningcited by 20
  19. 2023Latent Traversals in Generative Models as Potential Flowscited by 17
  20. 2023TFS-ViT: Token-Level Feature Stylization for Domain Generalizationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026CrossFlowDG: Bridging the Modality Gap with Cross-modal Flow Matching for Domain Generalizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024DGMamba: Domain Generalization via Generalized State Space Model
  2. 2024START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
  3. 2026Domain Generalization via Text-Anchored Information Bottleneck
  4. 2025Domain Generalization via Discrete Codebook Learning
  5. 2025Latent Domain Prompt Learning for Vision-Language Models
  6. 2026SHED: Style-Homogenized Embedding Alignment for Domain Generalization
  7. 2024PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization
  8. 2024DPStyler: Dynamic PromptStyler for Source-Free Domain Generalization