UniForm shares one attention matrix across all attention heads and adds multi-scale depthwise convolutions to value projections, claiming faster edge inference at comparable accuracy.
DHA: learning decoupled-head attention from transformer checkpoints via adaptive heads fusion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
REJECT 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
UniForm: A Reuse Attention Mechanism Optimized for Efficient Vision Transformers on Edge Devices
UniForm shares one attention matrix across all attention heads and adds multi-scale depthwise convolutions to value projections, claiming faster edge inference at comparable accuracy.