SegMoTE: Token-Level Mixture of Experts for Medical Image Segmentation
Yujie Lu1, Jingwen Li2, Sibo Ju3, Yanzhou Su4, He Yao1, Yisong Liu1, Min Zhu1†, Junlong Cheng1†
1Sichuan University
2Xinjiang University
3Fuzhou University
4Alibaba DAMO Academy
CVPR 2026 (Oral)
Medical image segmentation requires robust adaptation across heterogeneous
modalities and anatomical structures, while pixel-level annotation remains
expensive. SegMoTE is an efficient adaptation framework built on the Segment
Anything Model (SAM). It introduces a token-level Mixture of Experts
(MoTE) mechanism that dynamically selects modality-adaptive expert tokens,
and a Progressive Prompt Tokenization (PPT) module that learns
feature-conditioned prompts for prompt-free segmentation on suitable
foreground-background tasks. Trained on the curated MedSeg-HQ dataset,
SegMoTE aims to retain the flexible prompt interface and generalization ability
of SAM while providing lightweight adaptation for multimodal medical image
segmentation.
1@article{lu2026segmote,
2 title={SegMoTE: Token-Level Mixture of Experts for Medical Image Segmentation},
3 author={Lu, Yujie and Li, Jingwen and Ju, Sibo and Su, Yanzhou and Liu, Yisong and Zhu, Min and Cheng, Junlong and others},
4 journal={arXiv preprint arXiv:2602.19213},
5 year={2026}
6}
