English

GuiDINO: Rethinking Vision Foundation Model in Medical Image Segmentation

Computer Vision and Pattern Recognition 2026-03-03 v1

Abstract

Foundation vision models are increasingly adopted in medical image analysis. Due to domain shift, these pretrained models misalign with medical image segmentation needs without being fully fine-tuned or lightly adapted. We introduce GuiDINO, a framework that repositions native foundation model to acting as a visual guidance generator for downstream segmentation. GuiDINO extracts visual feature representation from DINOv3 and converts them into a spatial guide mask via a lightweight TokenBook mechanism, which aggregates token-prototype similarities. This guide mask gates feature activations in multiple segmentation backbones, thereby injecting foundation-model priors while preserving the inductive biases and efficiency of medical dedicated architectures. Training relies on a guide supervision objective loss that aligns the guide mask to ground-truth regions, optionally augmented by a boundary-focused hinge loss to sharpen fine structures. GuiDINO also supports parameter-efficient adaptation through LoRA on the DINOv3 guide backbone. Across diverse medical datasets and nnUNet-style inference, GuiDINO consistently improves segmentation quality and boundary robustness, suggesting a practical alternative to fine-tuning and offering a new perspective on how foundation models can best serve medical vision. Code is available at https://github.com/Hi-FishU/GuiDINO

Keywords

Cite

@article{arxiv.2603.01115,
  title  = {GuiDINO: Rethinking Vision Foundation Model in Medical Image Segmentation},
  author = {Zhuonan Liang and Wei Guo and Jie Gan and Yaxuan Song and Runnan Chen and Hang Chang and Weidong Cai},
  journal= {arXiv preprint arXiv:2603.01115},
  year   = {2026}
}

Comments

12 pages, 2 figures, 3 tables