Longlong Yu

2D-CrossScan Mamba: Enhancing State Space Models with Spatially Consistent Multi-Path 2D Information Propagation

Despite recent progress in adapting State Space Models such as Mamba to vision tasks, their intrinsic 1D scanning mechanism imposes limitations when applied to inherently 2D-structured data like images. Existing adaptations, including VMamba and 2DMamba, either suffer from inconsistency between scan