Pruning visual tokens degrades visual grounding because position IDs become misaligned; preserving the original position IDs recovers most of the lost accuracy with no extra cost.
Chasing sparsity in vision transform- ers: An end-to-end exploration
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
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning
Pruning visual tokens degrades visual grounding because position IDs become misaligned; preserving the original position IDs recovers most of the lost accuracy with no extra cost.