Advancing Cross-Organ Domain Generalization with Test-Time Style Transfer and Diversity Enhancement
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_ | 1866916660743503872 |
|---|---|
| author | Meng, Biwen Long, Xi Yang, Wanrong Liu, Ruochen Tian, Yi Zheng, Yalin Liu, Jingxin |
| author_facet | Meng, Biwen Long, Xi Yang, Wanrong Liu, Ruochen Tian, Yi Zheng, Yalin Liu, Jingxin |
| contents | Deep learning has made significant progress in addressing challenges in various fields including computational pathology (CPath). However, due to the complexity of the domain shift problem, the performance of existing models will degrade, especially when it comes to multi-domain or cross-domain tasks. In this paper, we propose a Test-time style transfer (T3s) that uses a bidirectional mapping mechanism to project the features of the source and target domains into a unified feature space, enhancing the generalization ability of the model. To further increase the style expression space, we introduce a Cross-domain style diversification module (CSDM) to ensure the orthogonality between style bases. In addition, data augmentation and low-rank adaptation techniques are used to improve feature alignment and sensitivity, enabling the model to adapt to multi-domain inputs effectively. Our method has demonstrated effectiveness on three unseen datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18567 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advancing Cross-Organ Domain Generalization with Test-Time Style Transfer and Diversity Enhancement Meng, Biwen Long, Xi Yang, Wanrong Liu, Ruochen Tian, Yi Zheng, Yalin Liu, Jingxin Computer Vision and Pattern Recognition Deep learning has made significant progress in addressing challenges in various fields including computational pathology (CPath). However, due to the complexity of the domain shift problem, the performance of existing models will degrade, especially when it comes to multi-domain or cross-domain tasks. In this paper, we propose a Test-time style transfer (T3s) that uses a bidirectional mapping mechanism to project the features of the source and target domains into a unified feature space, enhancing the generalization ability of the model. To further increase the style expression space, we introduce a Cross-domain style diversification module (CSDM) to ensure the orthogonality between style bases. In addition, data augmentation and low-rank adaptation techniques are used to improve feature alignment and sensitivity, enabling the model to adapt to multi-domain inputs effectively. Our method has demonstrated effectiveness on three unseen datasets. |
| title | Advancing Cross-Organ Domain Generalization with Test-Time Style Transfer and Diversity Enhancement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.18567 |