Metraipolis › archive › dc_ec0fe41fba9b
Learning from Unlabeled Photographs for General Oral Image Analysis — arXiv:2611.04709
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04709
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T19:03:25.034Z
- SHA-256 of the archived text
00d4efd5903415352d172c9dc3874b7c94cf7cd384ab9fce9181b126ae8832c1- Stable URL of this page
https://metraipolis.com/documento/dc_ec0fe41fba9b
How to cite
Learning from Unlabeled Photographs for General Oral Image Analysis — arXiv:2611.04709 — arXiv (en), https://arxiv.org/abs/2611.04709 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec0fe41fba9b (Metraipolis archive dc_ec0fe41fba9b, sha256 00d4efd5903415352d172c9dc3874b7c94cf7cd384ab9fce9181b126ae8832c1)
BibTeX
@misc{dcec0fe41fba9b,
title = {Learning from Unlabeled Photographs for General Oral Image Analysis — arXiv:2611.04709},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04709},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec0fe41fba9b; sha256 00d4efd5903415352d172c9dc3874b7c94cf7cd384ab9fce9181b126ae8832c1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04709. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.04709 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-04T18:39:37.531Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).