SplitFed-CL: A Split Federated Co-Learning Framework for Medical Image Segmentation with Inaccurate Labels
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913113565036544 |
|---|---|
| author | Kafshgari, Zahra Hafezi Hadizadeh, Hadi Saeedi, Parvaneh |
| author_facet | Kafshgari, Zahra Hafezi Hadizadeh, Hadi Saeedi, Parvaneh |
| contents | Split Federated Learning (SplitFed) combines federated and split learning to preserve privacy while reducing client-side computation. However, in medical image segmentation, heterogeneous label quality across clients can significantly degrade performance. We propose SplitFed-CL, a co-learning framework where a global teacher guides local students to detect and refine unreliable annotations. Reliable labels supervise training directly, while unreliable labels are corrected via weighted student--teacher refinement. SplitFed-CL further incorporates consistency regularization for robustness to input perturbations and a trainable weighting module to balance loss terms adaptively. We also introduce a novel difficulty guided strategy to simulate human like boundary centric annotation errors, where the degree of perturbation is governed by shape complexity and the associated annotation difficulty. Experiments on two multiclass segmentation datasets with controlled synthetic noise, together with a binary segmentation dataset containing real-world annotation errors, demonstrate that SplitFed-CL consistently outperforms seven state-of-the-art baselines, yielding improved segmentation quality and robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11060 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SplitFed-CL: A Split Federated Co-Learning Framework for Medical Image Segmentation with Inaccurate Labels Kafshgari, Zahra Hafezi Hadizadeh, Hadi Saeedi, Parvaneh Image and Video Processing Computer Vision and Pattern Recognition Split Federated Learning (SplitFed) combines federated and split learning to preserve privacy while reducing client-side computation. However, in medical image segmentation, heterogeneous label quality across clients can significantly degrade performance. We propose SplitFed-CL, a co-learning framework where a global teacher guides local students to detect and refine unreliable annotations. Reliable labels supervise training directly, while unreliable labels are corrected via weighted student--teacher refinement. SplitFed-CL further incorporates consistency regularization for robustness to input perturbations and a trainable weighting module to balance loss terms adaptively. We also introduce a novel difficulty guided strategy to simulate human like boundary centric annotation errors, where the degree of perturbation is governed by shape complexity and the associated annotation difficulty. Experiments on two multiclass segmentation datasets with controlled synthetic noise, together with a binary segmentation dataset containing real-world annotation errors, demonstrate that SplitFed-CL consistently outperforms seven state-of-the-art baselines, yielding improved segmentation quality and robustness. |
| title | SplitFed-CL: A Split Federated Co-Learning Framework for Medical Image Segmentation with Inaccurate Labels |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.11060 |