DINOv2: Learning Robust Visual Features without Supervision
2023 · arXiv (Cornell University) · 1,011 citations
https://doi.org/10.48550/arxiv.2304.07193
M
Maxime Oquab
Claim or correct this author profile
Claim this profile or suggest corrections to the name, affiliation, bio, photo, or paper titles. Approved changes appear as verified CitedEvidence overlays.
38
Papers
5.8K
Citations
12
h-index
14
i10-index
Maxime Oquab is an academic researcher. The author has contributed to research in topics: Advanced Neural Network Applications & Domain Adaptation and Few-Shot Learning & Generative Adversarial Networks and Image Synthesis. The author has an h-index of 12, co-authored 33 publications.
Papers by this author
worksIs object localization for free? - Weakly-supervised learning with convolutional neural networks
2015 · 917 citations
https://doi.org/10.1109/cvpr.2015.7298668
Learning and transferring mid-level image representations using convolutional neural networks
2014 · 36 citations
Back-to-back regression: Disentangling the influence of correlated factors from multivariate observations
2020 · NeuroImage · 17 citations
https://doi.org/10.1016/j.neuroimage.2020.117028
DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
2025 · 9 citations
https://doi.org/10.1109/cvpr52734.2025.02319
Research topics
topicsChat about Author
Papers
Chat
Click to start Chat