Computer vision & multimodal· 2023
DINOv2: Learning Robust Visual Features without Supervision
On the reading lists
- #280 in the Top 500 (2026 edition)
- #51 in Computer vision & multimodal (2026 edition)
Why it matters
Established powerful general-purpose visual embeddings through scaled self-supervised pretraining and curated data.
Condensed from the expert lists' notes.
The record
- First released
- 2023 (from arXiv 2304.07193)
- Published
- 2024
- Citations
- 11,351 citations, as counted by Papers With Code (CC BY-SA 4.0)
- Named by
- both expert lists
- Score
- 0.458 · computed rank 280 · consensus 0.31, must-read 0.5, citations percentile 0.901 (2020s · vision), awards 0, existing lists 0. Method
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.