DINOv2: Learning Robust Visual Features without Supervision
Work
Year: 2023
Type: preprint
Abstract: The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could great... more
Source: arXiv (Cornell University)
Institutions Institut national de recherche en informatique et en automatique, Université Paris-Saclay
Cites: 131
Cited by: 513
Related to: 10
Citation percentile (by year/subfield): 99.99
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Sustainable Development Goal Quality education
Open Access status: green