SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916927850414080 |
|---|---|
| author | Yang, Sicheng Wang, Hongqiu Xing, Zhaohu Chen, Sixiang Zhu, Lei |
| author_facet | Yang, Sicheng Wang, Hongqiu Xing, Zhaohu Chen, Sixiang Zhu, Lei |
| contents | The DINO family of self-supervised vision models has shown remarkable transferability, yet effectively adapting their representations for segmentation remains challenging. Existing approaches often rely on heavy decoders with multi-scale fusion or complex upsampling, which introduce substantial parameter overhead and computational cost. In this work, we propose SegDINO, an efficient segmentation framework that couples a frozen DINOv3 backbone with a lightweight decoder. SegDINO extracts multi-level features from the pretrained encoder, aligns them to a common resolution and channel width, and utilizes a lightweight MLP head to directly predict segmentation masks. This design minimizes trainable parameters while preserving the representational power of foundation features. Extensive experiments across six benchmarks, including three medical datasets (TN3K, Kvasir-SEG, ISIC) and three natural image datasets (MSD, VMD-D, ViSha), demonstrate that SegDINO consistently achieves state-of-the-art performance compared to existing methods. Code is available at https://github.com/script-Yang/SegDINO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00833 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3 Yang, Sicheng Wang, Hongqiu Xing, Zhaohu Chen, Sixiang Zhu, Lei Computer Vision and Pattern Recognition The DINO family of self-supervised vision models has shown remarkable transferability, yet effectively adapting their representations for segmentation remains challenging. Existing approaches often rely on heavy decoders with multi-scale fusion or complex upsampling, which introduce substantial parameter overhead and computational cost. In this work, we propose SegDINO, an efficient segmentation framework that couples a frozen DINOv3 backbone with a lightweight decoder. SegDINO extracts multi-level features from the pretrained encoder, aligns them to a common resolution and channel width, and utilizes a lightweight MLP head to directly predict segmentation masks. This design minimizes trainable parameters while preserving the representational power of foundation features. Extensive experiments across six benchmarks, including three medical datasets (TN3K, Kvasir-SEG, ISIC) and three natural image datasets (MSD, VMD-D, ViSha), demonstrate that SegDINO consistently achieves state-of-the-art performance compared to existing methods. Code is available at https://github.com/script-Yang/SegDINO. |
| title | SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3 |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.00833 |