AI RESEARCH
SF-Mamba: Rethinking State Space Model for Vision
arXiv CS.AI
•
ArXi:2603.16423v1 Announce Type: cross The realm of Mamba for vision has been advanced in recent years to strike for the alternatives of Vision Transformers (ViTs) that suffer from the quadratic complexity. While the recurrent scanning mechanism of Mamba offers computational efficiency, it inherently limits non-causal interactions between image patches. Prior works have attempted to address this limitation through various multi-scan strategies; however, these approaches suffer from inefficiencies due to suboptimal scan designs and frequent data rearrangement.