DinoDental: Benchmarking DINOv3 as a Unified Vision Encoder for Dental Image Analysis

TL;DR

DinoDental systematically evaluates DINOv3 as a versatile, off-the-shelf encoder for dental image analysis, demonstrating its effectiveness across various tasks and imaging modalities without domain-specific pre-training.

Contribution

The paper introduces DinoDental, a comprehensive benchmark for assessing DINOv3's transferability and performance in dental imaging tasks, including analysis of adaptation strategies and model scaling.

Findings

DINOv3 performs well across dental image analysis tasks.

Scaling model size and input resolution improves performance.

Different adaptation strategies affect transfer effectiveness.

Abstract

The scarcity and high cost of expert annotations in dental imaging present a significant challenge for the development of AI in dentistry. DINOv3, a state-of-the-art, self-supervised vision foundation model pre-trained on 1.7 billion images, offers a promising pathway to mitigate this issue. However, its reliability when transferred to the dental domain, with its unique imaging characteristics and clinical subtleties, remains unclear. To address this, we introduce DinoDental, a unified benchmark designed to systematically evaluate whether DINOv3 can serve as a reliable, off-the-shelf encoder for comprehensive dental image analysis without requiring domain-specific pre-training. Constructed from multiple public datasets, DinoDental covers a wide range of tasks, including classification, detection, and instance segmentation on both panoramic radiographs and intraoral photographs. We further analyze the model's transfer performance by scaling its size and input resolution, and by comparing different adaptation strategies, including frozen features, full fine-tuning, and the parameter-efficient Low-Rank Adaptation (LoRA) method. Our experiments show that DINOv3 can serve as a strong unified encoder for dental image analysis across both panoramic radiographs and intraoral photographs, remaining competitive across tasks while showing particularly clear advantages for intraoral image understanding and boundary-sensitive dense prediction. Collectively, DinoDental provides a systematic framework for comprehensively evaluating DINOv3 in dental analysis, establishing a foundational benchmark to guide efficient and effective model selection and adaptation for the dental AI community.