AI RESEARCH
MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models
arXiv CS.CV
•
ArXi:2603.20074v1 Announce Type: new State Space Models (SSMs), especially recent Mamba architecture, have achieved remarkable success in sequence modeling tasks. However, extending SSMs to computer vision remains challenging due to the non-sequential structure of visual data and its complex 2D spatial dependencies. Although several early studies have explored adapting selective SSMs for vision applications, most approaches primarily depend on employing various traversal strategies over the same input. This