A lightweight decoupled embedding, trained through a differentiable approximation of token merging, improves the speed-accuracy trade-off of Vision Transformers.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
A lightweight decoupled embedding, trained through a differentiable approximation of token merging, improves the speed-accuracy trade-off of Vision Transformers.