Under a fixed 80k-update budget, DINOv2 dominates semantic benchmarks, VideoMAE dominates geometric ones, and their combination balances the two at a measurable cost.
In: International Conference on Learning Representations (ICLR) (2022), https://openreview.net/forum?id=p-BhZSz59o4
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Controlled Study of Self-Supervised Image and Video Pretraining under Limited Resources
Under a fixed 80k-update budget, DINOv2 dominates semantic benchmarks, VideoMAE dominates geometric ones, and their combination balances the two at a measurable cost.