Shared feature and sampling banks fed to every decoder block improve monocular depth estimation accuracy slightly for ViT and RepViT encoders at under 1% parameter overhead for ViTs.
Eva: Exploring the limits of masked visual representation learning at scale,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Rethinking Encoder-Decoder Flow Through Shared Structures
Shared feature and sampling banks fed to every decoder block improve monocular depth estimation accuracy slightly for ViT and RepViT encoders at under 1% parameter overhead for ViTs.