Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models
Puskal Khadka, KC Santosh
State Space Models (SSMs), especially recent Mamba architecture, have achieved remarkable success in sequence modeling tasks. However, extending SSMs to computer vision remains cha…
cs.CV2025
CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision
Puskal Khadka, Rodrigue Rizk, Longwei Wang +1
Vision Transformers (ViTs) have achieved impressive results in computer vision by leveraging self-attention to model long-range dependencies. However, their emphasis on global cont…