metadata
base_model: facebook/dinov3-vitl16-pretrain-lvd1689m
tags:
- dinov3
- onnx
- facebook
DINOv3 (ONNX)
ONNX export of a fine-tuned DINOv3 vision backbone.
License
This model is a derivative of DINOv3 by Meta, distributed under the DINOv3 License.
Source
- Base model:
facebook/dinov3-vitl16-pretrain-lvd1689m - Fine-tuned, then exported to ONNX
Citation
@misc{simeoni2025dinov3,
title={{DINOv3}},
author={Sim{\'e}oni, Oriane and Vo, Huy V. and Seitzer, Maximilian and Baldassarre, Federico and Oquab, Maxime and Jose, Cijo and Khalidov, Vasil and Szafraniec, Marc and Yi, Seungeun and Ramamonjisoa, Micha{\"e}l and Massa, Francisco and Haziza, Daniel and Wehrstedt, Luca and Wang, Jianyuan and Darcet, Timoth{\'e}e and Moutakanni, Th{\'e}o and Sentana, Leonel and Roberts, Claire and Vedaldi, Andrea and Tolan, Jamie and Brandt, John and Couprie, Camille and Mairal, Julien and J{\'e}gou, Herv{\'e} and Labatut, Patrick and Bojanowski, Piotr},
year={2025},
eprint={2508.10104},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2508.10104},
}