Semi-MoE: Mixture-of-Experts meets Semi-Supervised Histopathology Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916954516750336 |
|---|---|
| author | Vu, Nguyen Lan Vi Nguyen, Thanh-Huy Nguyen, Thien Kihara, Daisuke Wang, Tianyang Li, Xingjian Xu, Min |
| author_facet | Vu, Nguyen Lan Vi Nguyen, Thanh-Huy Nguyen, Thien Kihara, Daisuke Wang, Tianyang Li, Xingjian Xu, Min |
| contents | Semi-supervised learning has been employed to alleviate the need for extensive labeled data for histopathology image segmentation, but existing methods struggle with noisy pseudo-labels due to ambiguous gland boundaries and morphological misclassification. This paper introduces Semi-MOE, to the best of our knowledge, the first multi-task Mixture-of-Experts framework for semi-supervised histopathology image segmentation. Our approach leverages three specialized expert networks: A main segmentation expert, a signed distance field regression expert, and a boundary prediction expert, each dedicated to capturing distinct morphological features. Subsequently, the Multi-Gating Pseudo-labeling module dynamically aggregates expert features, enabling a robust fuse-and-refine pseudo-labeling mechanism. Furthermore, to eliminate manual tuning while dynamically balancing multiple learning objectives, we propose an Adaptive Multi-Objective Loss. Extensive experiments on GlaS and CRAG benchmarks show that our method outperforms state-of-the-art approaches in low-label settings, highlighting the potential of MoE-based architectures in advancing semi-supervised segmentation. Our code is available at https://github.com/vnlvi2k3/Semi-MoE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13834 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Semi-MoE: Mixture-of-Experts meets Semi-Supervised Histopathology Segmentation Vu, Nguyen Lan Vi Nguyen, Thanh-Huy Nguyen, Thien Kihara, Daisuke Wang, Tianyang Li, Xingjian Xu, Min Computer Vision and Pattern Recognition Semi-supervised learning has been employed to alleviate the need for extensive labeled data for histopathology image segmentation, but existing methods struggle with noisy pseudo-labels due to ambiguous gland boundaries and morphological misclassification. This paper introduces Semi-MOE, to the best of our knowledge, the first multi-task Mixture-of-Experts framework for semi-supervised histopathology image segmentation. Our approach leverages three specialized expert networks: A main segmentation expert, a signed distance field regression expert, and a boundary prediction expert, each dedicated to capturing distinct morphological features. Subsequently, the Multi-Gating Pseudo-labeling module dynamically aggregates expert features, enabling a robust fuse-and-refine pseudo-labeling mechanism. Furthermore, to eliminate manual tuning while dynamically balancing multiple learning objectives, we propose an Adaptive Multi-Objective Loss. Extensive experiments on GlaS and CRAG benchmarks show that our method outperforms state-of-the-art approaches in low-label settings, highlighting the potential of MoE-based architectures in advancing semi-supervised segmentation. Our code is available at https://github.com/vnlvi2k3/Semi-MoE. |
| title | Semi-MoE: Mixture-of-Experts meets Semi-Supervised Histopathology Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.13834 |