A patch pruning method for ViTs that uses cross-head variance (and median absolute deviation) of class-token attention weights as an importance score, with a fusion token and overlapping patch embeddings.
In CVPR (2009)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Patch Pruning Strategy Based on Robust Statistical Measures of Attention Weight Diversity in Vision Transformers
A patch pruning method for ViTs that uses cross-head variance (and median absolute deviation) of class-token attention weights as an importance score, with a fusion token and overlapping patch embeddings.