DGFamba: Learning Flow Factorized State Space for Visual Domain Generalization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909574888423424 |
|---|---|
| author | Bi, Qi Yi, Jingjun Zheng, Hao Zhan, Haolan Ji, Wei Huang, Yawen Li, Yuexiang |
| author_facet | Bi, Qi Yi, Jingjun Zheng, Hao Zhan, Haolan Ji, Wei Huang, Yawen Li, Yuexiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_08019 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DGFamba: Learning Flow Factorized State Space for Visual Domain Generalization Bi, Qi Yi, Jingjun Zheng, Hao Zhan, Haolan Ji, Wei Huang, Yawen Li, Yuexiang Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | DGFamba: Learning Flow Factorized State Space for Visual Domain Generalization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.08019 |