0
DINOv2: Learning Robust Visual Features without Supervision
Maxime Oquab, Timothée Darcet, Théo Moutakanni et al., 2023. arXiv.
Introduces DINOv2, a family of vision models trained without labels to produce general-purpose image features.
What it's used for here
The emerging-methods survey proposes it, with Segment Anything and CLIP, for unsupervised clustering and segmentation of glyphs.
Cited by on this site 1 record
1 methods surveys
SRCMathematics
Cite it
Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., Assran, M., Ballas, N., Galuba, W., Howes, R., Huang, P. Y., Li, S. W., Misra, I., Rabbat, M., Sharma, V., Synnaeve, G., Xu, H., Jegou, H., Mairal, J., Labatut, P., Joulin, A., & Bojanowski, P. (2023). DINOv2: Learning Robust Visual Features without Supervision. arXiv. https://arxiv.org/abs/2304.07193
@article{oquab2023dinov2,
author = {Oquab, Maxime and Darcet, Timothée and Moutakanni, Théo and Vo, Huy and Szafraniec, Marc and Khalidov, Vasil and Fernandez, Pierre and Haziza, Daniel and Massa, Francisco and El-Nouby, Alaaeldin and Assran, Mahmoud and Ballas, Nicolas and Galuba, Wojciech and Howes, Russell and Huang, Po-Yao and Li, Shang-Wen and Misra, Ishan and Rabbat, Michael and Sharma, Vasu and Synnaeve, Gabriel and Xu, Hu and Jegou, Hervé and Mairal, Julien and Labatut, Patrick and Joulin, Armand and Bojanowski, Piotr},
title = {DINOv2: Learning Robust Visual Features without Supervision},
journal = {arXiv},
year = {2023},
url = {https://arxiv.org/abs/2304.07193}
}TY - GEN TI - DINOv2: Learning Robust Visual Features without Supervision AU - Oquab, Maxime AU - Darcet, Timothée AU - Moutakanni, Théo AU - Vo, Huy AU - Szafraniec, Marc AU - Khalidov, Vasil AU - Fernandez, Pierre AU - Haziza, Daniel AU - Massa, Francisco AU - El-Nouby, Alaaeldin AU - Assran, Mahmoud AU - Ballas, Nicolas AU - Galuba, Wojciech AU - Howes, Russell AU - Huang, Po-Yao AU - Li, Shang-Wen AU - Misra, Ishan AU - Rabbat, Michael AU - Sharma, Vasu AU - Synnaeve, Gabriel AU - Xu, Hu AU - Jegou, Hervé AU - Mairal, Julien AU - Labatut, Patrick AU - Joulin, Armand AU - Bojanowski, Piotr PY - 2023 JO - arXiv UR - https://arxiv.org/abs/2304.07193 ER -
Oquab, Maxime et al.. “DINOv2: Learning Robust Visual Features without Supervision.” arXiv (2023).