cs.CVNov 3, 2026

Learning from Unlabeled Photographs for General Oral Image Analysis

Authors: Zhong-Shi Zhang, Zi-Li Yu, Xiao Xiao, Huan Liu, Gui-Song Xia, Cui Huang, Meng-Xun Li

Organizations: State Key Laboratory of Oral & Maxillofacial Reconstruction and Regeneration, Key Laboratory of Oral Biomedicine, Ministry of Education, Hubei Key Laboratory of Stomatology, School and Hospital of Stomatology, Wuhan University, China · Department of Oral Maxillofacial Surgery, School and Hospital of Stomatology, Wuhan University, China · Department of Prosthodontics, School and Hospital of Stomatology, Wuhan University, China · Department of Periodontology, School and Hospital of Stomatology, Wuhan University, China · 

Abstract

Oral photographs contain rich clinical information and hold significant potential for artificial intelligence applications; however, most models are trained for individual tasks and rely on costly expert annotations. We hypothesized that self-supervised training on unlabeled oral photographs could produce transferable visual representations for heterogeneous vision tasks. To test this hypothesis, we developed DOVE (Dental Optical Visual Encoder) by domain-adaptive self-supervised pretraining on approximately 530,000 unlabeled oral photographs collected from publicly accessible sources. DOVE was benchmarked against 3 established baselines across 5 classification datasets and 4 segmentation datasets, covering both frozen backbone evaluation and end-to-end finetuning. DOVE achieved the strongest overall performance, ranking best in few-shot transfer and label efficiency on most benchmarks. Under the 20-shot frozen-backbone protocol, DOVE outperformed the second best DINOv3 by 4.37 percentage points in mean macro-F1 across classification datasets and by 4.49 percentage points in mean macro-Dice across segmentation tasks. Under end-to-end finetuning, DOVE achieved at least 80% of the strongest full-data baseline's performance across most evaluation datasets using only 10% of the labeled training data. Qualitative retrieval and feature analyses further indicated better organization of image-level and spatial representations. These findings support DOVE as a generalizable and label-efficient backbone for oral vision research.

Explore similar work

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

    Mar 30, 2026Kun Tang, Xinquan Yang, Mianjie Zheng +6Medical Image AnalysisVision Foundation Model Adaptation

  2. MetaDent: Labeling Clinical Images for Vision-Language Models in Dentistry

    Apr 16, 2026Meng-Xun Li, Wen-Hui Deng, Zhi-Xing Wu +6VLM EvaluationMedical Image Analysis

  3. Large AI Models in Dental Healthcare: From General-Purpose Systems to Domain-Specific Foundation Models

    Jun 1, 2026Sema Helali, Lina Abu Nada, Sausan Al Kawas +3Medical Imaging Foundation ModelsMedical VLMs