RPAttention achieves linear-complexity global attention in Vision Transformers by performing token compression in representation space via a Gather-Interact-Distribute process with learned representatives.
CutMix: Regularization strategy to train strong classifiers with localizable features
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Representative Attention For Vision Transformers
RPAttention achieves linear-complexity global attention in Vision Transformers by performing token compression in representation space via a Gather-Interact-Distribute process with learned representatives.