Spread Too Thin: How Higher Resolution Dilutes a Vision Transformer's Attention, and a Training-Free Rescaling
A vision transformer read at a higher resolution than it was trained at spreads each attention row over many more patches, yet every row must still hand out exactly one unit of weight.
By Neil D. B. BrucearXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Nov 17, 2026.
Comments
Sign in to join the discussion.