Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution.
Mostafa DehghaniBasil MustafaJosip DjolongaJonathan HeekMatthias MindererMathilde CaronAndreas SteinerJoan PuigcerverRobert GeirhosIbrahim M. AlabdulmohsinAvital OliverPiotr PadlewskiAlexey A. GritsenkoMario LucicNeil HoulsbyPublished in: NeurIPS (2023)