Showing cs.CVShow all
2 papers · 1 filter
cs.CV2024
Fusion of regional and sparse attention in Vision Transformers
Nabil Ibtehaz, Ning Yan, Masood Mortazavi +1
Modern vision transformers leverage visually inspired local interaction between pixels through attention computed within window or grid regions, in contrast to the global attention…
cs.CV2024
ACC-ViT : Atrous Convolution's Comeback in Vision Transformers
Nabil Ibtehaz, Ning Yan, Masood Mortazavi +1
Transformers have elevated to the state-of-the-art vision architectures through innovations in attention mechanism inspired from visual perception. At present two classes of attent…