DINOv2: Learning Robust Visual Features without Supervision.

Maxime Oquab Timothée Darcet Théo Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby Mahmoud Assran Nicolas Ballas Wojciech Galuba Russell Howes Po-Yao Huang Shang-Wen Li Ishan Misra Michael G. Rabbat Vasu Sharma Gabriel Synnaeve Hu Xu Hervé Jégou Julien Mairal Patrick Labatut Armand Joulin Piotr Bojanowski

Published in: CoRR (2023)

Keyphrases

visual features
image retrieval
active learning
low level
visual content
visual appearance
learning algorithm
image search
image classification
visual information
image collections
semantic concepts
low level features
semantic gap
bag of features
visual patterns