EffiCell-Seg achieves superior cell segmentation across imaging modalities with ~5M trainable parameters by using a Cell Structure Prompt Encoder and Synergistic Mask Decoder on frozen VFM features.
Dino U-Net: Exploiting High-Fidelity Dense Features from Foundation Models for Medical Image Segmentation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Foundation models pre-trained on large-scale natural image datasets offer a powerful paradigm for medical image segmentation. However, effectively transferring their learned representations for precise clinical applications remains a challenge. In this work, we propose Dino U-Net, a novel encoder-decoder architecture designed to exploit the high-fidelity dense features of the DINOv3 vision foundation model. Our architecture introduces an encoder built upon a frozen DINOv3 backbone, which employs a specialized adapter to fuse the model's rich semantic features with low-level spatial details. To preserve the quality of these representations during dimensionality reduction, we design a new fidelity-aware projection module (FAPM) that effectively refines and projects the features for the decoder. We conducted extensive experiments on seven diverse public medical image segmentation datasets. Our results show that Dino U-Net achieves state-of-the-art performance, consistently outperforming previous methods across various imaging modalities. Our framework proves to be highly scalable, with segmentation accuracy consistently improving as the backbone model size increases up to the 7-billion-parameter variant. The findings demonstrate that leveraging the superior, dense-pretrained features from a general-purpose foundation model provides a highly effective and parameter-efficient approach to advance the accuracy of medical image segmentation. The code is available at https://github.com/yifangao112/DinoUNet.
fields
cs.CV 5years
2026 5verdicts
UNVERDICTED 5representative citing papers
Dino-NestedUNet improves pathology tumor segmentation by coupling DINOv3 encoders with dense nested decoding, showing gains over UNet++ and Dino-UNet baselines across multiple cohorts including zero-shot tests.
SegDINO adds Token Pyramid Adaptation and Scale-Aware Decoding to DINOv3 to deliver efficient state-of-the-art medical image segmentation on a new pancreatic CT dataset and public benchmarks.
HD-DinoMoE achieves 72.11% mean Dice and 58.44% mean IoU for multi-label scleral anomaly segmentation on the new ML-SASD-Mix benchmark while controlling false positives in specular regions.
DINO-Med3D progressively adapts DINOv3 for 3D medical segmentation via multi-slice embedding, segmentation proxy, 3D adapters, and parallel detail recovery, outperforming baselines on five public datasets.
citing papers explorer
-
Rethinking the Adaptation of Vision Foundation Models for Efficient Cell Segmentation
EffiCell-Seg achieves superior cell segmentation across imaging modalities with ~5M trainable parameters by using a Cell Structure Prompt Encoder and Synergistic Mask Decoder on frozen VFM features.
-
Dino-NestedUNet: Unlocking Foundation Vision Encoders for Pathology Tumor Bulk Segmentation via Dense Decoding
Dino-NestedUNet improves pathology tumor segmentation by coupling DINOv3 encoders with dense nested decoding, showing gains over UNet++ and Dino-UNet baselines across multiple cohorts including zero-shot tests.
-
SegDINO: Introducing Multi-Scale Structure into DINO for Efficient Medical Image Segmentation
SegDINO adds Token Pyramid Adaptation and Scale-Aware Decoding to DINOv3 to deliver efficient state-of-the-art medical image segmentation on a new pancreatic CT dataset and public benchmarks.
-
HD-DinoMoE: A Class-Aware Hierarchical Dual Mixture-of-Experts Network for Scleral Anomaly Segmentation in Complex Acquisition Scenarios
HD-DinoMoE achieves 72.11% mean Dice and 58.44% mean IoU for multi-label scleral anomaly segmentation on the new ML-SASD-Mix benchmark while controlling false positives in specular regions.
-
DINO-Med3D: Bridging Dimension and Domain Gaps in Volumetric Segmentation via Progressive Adaptation
DINO-Med3D progressively adapts DINOv3 for 3D medical segmentation via multi-slice embedding, segmentation proxy, 3D adapters, and parallel detail recovery, outperforming baselines on five public datasets.