ACC-ViT : Atrous Convolution's Comeback in Vision Transformers

arXiv:2403.04200v1 Announce Type: new
Abstract: 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 attentions prevail in vision transformers, regional and sparse attention. The former bounds the pixel interactions within a region; the latter spreads them across sparse grids. The opposing natures of them have resulted in a dilemma between either preserving hierarchical relation or attaining a global context. In this work, taking inspiration from atrous convolution, …

abstract acc architectures art arxiv attention convolution cs.cv innovations interactions perception pixel regional state them through transformers type vision vision transformers visual vit