A Survey on Visual Mamba

arXiv:2404.15956v1 Announce Type: new
Abstract: State space models (SSMs) with selection mechanisms and hardware-aware architectures, namely Mamba, have recently demonstrated significant promise in long-sequence modeling. Since the self-attention mechanism in transformers has quadratic complexity with image size and increasing computational demands, the researchers are now exploring how to adapt Mamba for computer vision tasks. This paper is the first comprehensive survey aiming to provide an in-depth analysis of Mamba models in the field of computer vision. It begins by exploring …

abstract adapt architectures arxiv attention complexity computational computer computer vision cs.cv hardware image mamba modeling researchers self-attention space ssms state state space models survey tasks transformers type vision visual