Domain-invariant Mixed-domain Semi-supervised Medical Image Segmentation with Clustered Maximum Mean Discrepancy Alignment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911394135277568 |
|---|---|
| author | Lam, Ba-Thinh Nguyen, Thanh-Huy Nguyen, Hoang-Thien Bui-Tran, Quang-Khai Vu, Nguyen Lan Vi Huynh, Phat K. Bagci, Ulas Xu, Min |
| author_facet | Lam, Ba-Thinh Nguyen, Thanh-Huy Nguyen, Hoang-Thien Bui-Tran, Quang-Khai Vu, Nguyen Lan Vi Huynh, Phat K. Bagci, Ulas Xu, Min |
| contents | Deep learning has shown remarkable progress in medical image semantic segmentation, yet its success heavily depends on large-scale expert annotations and consistent data distributions. In practice, annotations are scarce, and images are collected from multiple scanners or centers, leading to mixed-domain settings with unknown domain labels and severe domain gaps. Existing semi-supervised or domain adaptation approaches typically assume either a single domain shift or access to explicit domain indices, which rarely hold in real-world deployment. In this paper, we propose a domain-invariant mixed-domain semi-supervised segmentation framework that jointly enhances data diversity and mitigates domain bias. A Copy-Paste Mechanism (CPM) augments the training set by transferring informative regions across domains, while a Cluster Maximum Mean Discrepancy (CMMD) block clusters unlabeled features and aligns them with labeled anchors via an MMD objective, encouraging domain-invariant representations. Integrated within a teacher-student framework, our method achieves robust and precise segmentation even with very few labeled examples and multiple unknown domain discrepancies. Experiments on Fundus and M&Ms benchmarks demonstrate that our approach consistently surpasses semi-supervised and domain adaptation methods, establishing a potential solution for mixed-domain semi-supervised medical image segmentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16954 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Domain-invariant Mixed-domain Semi-supervised Medical Image Segmentation with Clustered Maximum Mean Discrepancy Alignment Lam, Ba-Thinh Nguyen, Thanh-Huy Nguyen, Hoang-Thien Bui-Tran, Quang-Khai Vu, Nguyen Lan Vi Huynh, Phat K. Bagci, Ulas Xu, Min Computer Vision and Pattern Recognition Deep learning has shown remarkable progress in medical image semantic segmentation, yet its success heavily depends on large-scale expert annotations and consistent data distributions. In practice, annotations are scarce, and images are collected from multiple scanners or centers, leading to mixed-domain settings with unknown domain labels and severe domain gaps. Existing semi-supervised or domain adaptation approaches typically assume either a single domain shift or access to explicit domain indices, which rarely hold in real-world deployment. In this paper, we propose a domain-invariant mixed-domain semi-supervised segmentation framework that jointly enhances data diversity and mitigates domain bias. A Copy-Paste Mechanism (CPM) augments the training set by transferring informative regions across domains, while a Cluster Maximum Mean Discrepancy (CMMD) block clusters unlabeled features and aligns them with labeled anchors via an MMD objective, encouraging domain-invariant representations. Integrated within a teacher-student framework, our method achieves robust and precise segmentation even with very few labeled examples and multiple unknown domain discrepancies. Experiments on Fundus and M&Ms benchmarks demonstrate that our approach consistently surpasses semi-supervised and domain adaptation methods, establishing a potential solution for mixed-domain semi-supervised medical image segmentation. |
| title | Domain-invariant Mixed-domain Semi-supervised Medical Image Segmentation with Clustered Maximum Mean Discrepancy Alignment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.16954 |