A boundary-forcing masked modeling paradigm for self-supervised vision pretraining yields a 1B model rivaling 7B models on dense spatial perception tasks.
Self-supervised learning from images with a joint-embedding predictive architecture
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
-
Vision Pretraining for Dense Spatial Perception
A boundary-forcing masked modeling paradigm for self-supervised vision pretraining yields a 1B model rivaling 7B models on dense spatial perception tasks.