mlsanityData to 7 Oct 2026

CrossFlowDG: Bridging the Modality Gap with Cross-modal Flow Matching for Domain Generalization

arXiv 2604.16892 ↗First posted 18 Apr 2026cs.CVcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Domain generalization (DG) aims to maintain performance under domain shift, which in computer vision appears primarily as stylistic variations that cause models to overfit to domain-specific appearance cues rather than class semantics. To overcome this, recent methods use textual representations as stable, domain-invariant anchors. However, multimodal approaches that rely on cosine similarity-based contrastive alignment leave a modality gap where image and text embeddings remain geometrically separated despite semantic correspondence. We propose CrossFlowDG, a novel DG framework that addresses this residual gap using noise-free, cross-modal flow matching. By learning a continuous transformation in the joint Euclidean latent space, our framework explicitly transports domain-biased image embeddings toward domain-invariant text embeddings of the correct class. Using the efficient VMamba image encoder and CLIP's text encoder, CrossFlowDG is tested against four common DG benchmarks, and achieves competitive performance on several benchmarks and state-of-the-art on TerraIncognita. Code is available at: https://github.com/ajkrit/CrossFlowDG

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 46 of its 54 references that are in the map. First posted on arXiv 18 Apr 2026.

Builds on

46 of 54 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025How to build a consistency model: Learning flow maps via self-distillation24 May
  2. 2024Flow map matching with stochastic interpolants: A mathematical framework for consistency models11 Jun

Other references · 44

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  9. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  10. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  11. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  12. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
32 more
  1. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  2. 2021Domain Generalization: A Surveycited by 760
  3. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  4. 2018Recognition in Terra Incognitacited by 655
  5. 2013Domain Generalization via Invariant Feature Representationcited by 622
  6. 2021Domain Generalization with MixStylecited by 563
  7. 2022Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learningcited by 553
  8. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
  9. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  10. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
  11. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  12. 2020Adaptive Risk Minimization: Learning to Adapt to Domain Shiftcited by 183
  13. 2017Domain Generalization by Marginal Transfer Learningcited by 180
  14. 2020Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularizationcited by 122
  15. 2021Causality-inspired Single-source Domain Generalization for Medical Image Segmentationcited by 118
  16. 2021Deep Generative Learning via Schr"odinger Bridgecited by 103
  17. 2023Sharpness-Aware Gradient Matching for Domain Generalizationcited by 102
  18. 2022Sparse Mixture-of-Experts are Domain Generalizable Learnerscited by 85
  19. 2014Domain-Adversarial Neural Networkscited by 78
  20. 2020Towards Universal Representation Learning for Deep Face Recognitioncited by 78
  21. 2021MixStyle Neural Networks for Domain Generalization and Adaptationcited by 64
  22. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 47
  23. 2022Self-Distilled Vision Transformer for Domain Generalizationcited by 35
  24. 2025FlowTok: Flowing Seamlessly Across Text and Image Tokenscited by 31
  25. 2024Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolutioncited by 26
  26. 2022Domain generalization of 3D semantic segmentation in autonomous drivingcited by 25
  27. 2024Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learningcited by 25
  28. 2024Rethinking Multi-domain Generalization with A General Learning Objectivecited by 23
  29. 2024DGMamba: Domain Generalization via Generalized State Space Modelcited by 21
  30. 2024V2X-DGW: Domain Generalization for Multi-agent Perception under Adverse Weather Conditionscited by 12
  31. 2024A Survey on Domain Generalization for Medical Image Analysiscited by 9
  32. 2025DGFamba: Learning Flow Factorized State Space for Visual Domain Generalizationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Variational Adapter for Cross-modal Similarity Representation
  2. 2025Exploring Cross-Modal Flows for Few-Shot Learning
  3. 2026SHED: Style-Homogenized Embedding Alignment for Domain Generalization
  4. 2024Cross-Modal Mapping: Mitigating the Modality Gap for Few-Shot Image Classification
  5. 2026BiCLIP: Domain Canonicalization via Structured Geometric Transformation
  6. 2026Direct Product Flow Matching: Decoupling Radial and Angular Dynamics for Few-Shot Adaptation
  7. 2025Enhancing CLIP Robustness via Cross-Modality Alignment
  8. 2023Choosing Wisely and Learning Deeply: Selective Cross-Modality Distillation via CLIP for Domain Generalization