Frequency-Based Federated Domain Generalization for Polyp Segmentation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915083091705856 |
|---|---|
| author | Pan, Hongyi Jha, Debesh Biswas, Koushik Bagci, Ulas |
| author_facet | Pan, Hongyi Jha, Debesh Biswas, Koushik Bagci, Ulas |
| contents | Federated Learning (FL) offers a powerful strategy for training machine learning models across decentralized datasets while maintaining data privacy, yet domain shifts among clients can degrade performance, particularly in medical imaging tasks like polyp segmentation. This paper introduces a novel Frequency-Based Domain Generalization (FDG) framework, utilizing soft-thresholding and hard-thresholding in the Fourier domain to address these challenges. By applying soft-thresholding and hard-thresholding to Fourier coefficients, our method generates new images with reduced background noise and enhances the model's ability to generalize across diverse medical imaging domains. Extensive experiments demonstrate substantial improvements in segmentation accuracy and domain robustness over baseline methods. This innovation integrates frequency domain techniques into FL, presenting a resilient approach to overcoming domain variability in decentralized medical image analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02044 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Frequency-Based Federated Domain Generalization for Polyp Segmentation Pan, Hongyi Jha, Debesh Biswas, Koushik Bagci, Ulas Image and Video Processing Federated Learning (FL) offers a powerful strategy for training machine learning models across decentralized datasets while maintaining data privacy, yet domain shifts among clients can degrade performance, particularly in medical imaging tasks like polyp segmentation. This paper introduces a novel Frequency-Based Domain Generalization (FDG) framework, utilizing soft-thresholding and hard-thresholding in the Fourier domain to address these challenges. By applying soft-thresholding and hard-thresholding to Fourier coefficients, our method generates new images with reduced background noise and enhances the model's ability to generalize across diverse medical imaging domains. Extensive experiments demonstrate substantial improvements in segmentation accuracy and domain robustness over baseline methods. This innovation integrates frequency domain techniques into FL, presenting a resilient approach to overcoming domain variability in decentralized medical image analysis. |
| title | Frequency-Based Federated Domain Generalization for Polyp Segmentation |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2410.02044 |