2 papers
cs.CV2022
PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers
Ryan Grainger, Thomas Paniagua, Xi Song +3
Vision Transformers (ViTs) are built on the assumption of treating image patches as ``visual tokens" and learn patch-to-patch attention. The patch embedding based tokenizer has a s…
math.NA2017
Conjugate gradient based acceleration for inverse problems
Sergey Voronin, Christophe Zaroli, Naresh P. Cuntoor
The conjugate gradient method is a widely used algorithm for the numerical solution of a system of linear equations. It is particularly attractive because it allows one to take adv…