A block-based attention pruning and fusion method for ViTs that reports large accuracy gains at reduced FLOPs, but the gain is mostly from the chunk-attention backbone and the core symmetry claim is false.
Twins: Revisiting the design of spatial attention in vision transformers
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
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers
A block-based attention pruning and fusion method for ViTs that reports large accuracy gains at reduced FLOPs, but the gain is mostly from the chunk-attention backbone and the core symmetry claim is false.