The advent of large-scale vision foundation models, pre-trained on diverse natural images, has marked a paradigm shift in computer vision. However, how the frontier vision foundation models' efficacies transfer to specialized domains remains such as medical imaging remains an open question. This report investigates whether DINOv3, a state-of-the-art self-supervised vision transformer (ViT) that features strong capability in dense prediction tasks, can directly serve as a powerful, unified encoder for medical vision tasks without domain-specific pre-training. To answer this, we benchmark DINOv3 across common medical vision tasks, including 2D/3D classification and segmentation on a wide range of medical imaging modalities. We systematically analyze its scalability by varying model sizes and input image resolutions. Our findings reveal that DINOv3 shows impressive performance and establishes a formidable new baseline. Remarkably, it can even outperform medical-specific foundation models like BiomedCLIP and CT-Net on several tasks, despite being trained solely on natural images. However, we identify clear limitations: The model's features degrade in scenarios requiring deep domain specialization, such as in Whole-Slide Pathological Images (WSIs), Electron Microscopy (EM), and Positron Emission Tomography (PET). Furthermore, we observe that DINOv3 does not consistently obey scaling law in the medical domain; performance does not reliably increase with larger models or finer feature resolutions, showing diverse scaling behaviors across tasks. Ultimately, our work establishes DINOv3 as a strong baseline, whose powerful visual features can serve as a robust prior for multiple complex medical tasks. This opens promising future directions, such as leveraging its features to enforce multiview consistency in 3D reconstruction.

翻译：基于多样化自然图像预训练的大规模视觉基础模型的出现，标志着计算机视觉领域的范式转变。然而，这些前沿视觉基础模型在医学影像等专业领域的效能迁移问题仍然悬而未决。本报告旨在探究DINOv3——一种在密集预测任务中表现出强大能力的最先进自监督视觉Transformer（ViT）模型——是否无需领域特定预训练即可直接作为医学视觉任务的强大统一编码器。为此，我们在涵盖多种医学影像模态的常见医学视觉任务（包括2D/3D分类与分割）上对DINOv3进行了基准测试。通过系统调整模型规模和输入图像分辨率，我们深入分析了其可扩展性。研究结果表明，DINOv3展现出卓越性能，树立了极具竞争力的新基准。值得注意的是，尽管仅使用自然图像训练，它在多项任务中甚至超越了BiomedCLIP、CT-Net等医学专用基础模型。然而，我们也发现其明显局限：在需要深度领域专业化的场景中（如全切片病理图像（WSI）、电子显微镜（EM）和正电子发射断层扫描（PET）），模型特征会出现退化。此外，我们观察到DINOv3在医学领域并未持续遵循缩放定律；更大模型或更精细特征分辨率并不能稳定提升性能，不同任务间呈现出多样化的缩放行为。最终，本研究确立了DINOv3作为强基准模型的地位，其强大的视觉特征可为多种复杂医学任务提供稳健的先验知识。这为未来研究开辟了前景广阔的方向，例如利用其特征增强三维重建中的多视角一致性。