Fusion of regional and sparse attention in Vision Transformers (2406.08859v1)

Abstract: Modern vision transformers leverage visually inspired local interaction between pixels through attention computed within window or grid regions, in contrast to the global attention employed in the original ViT. Regional attention restricts pixel interactions within specific regions, while sparse attention disperses them across sparse grids. These differing approaches pose a challenge between maintaining hierarchical relationships vs. capturing a global context. In this study, drawing inspiration from atrous convolution, we propose Atrous Attention, a blend of regional and sparse attention that dynamically integrates both local and global information while preserving hierarchical structures. Based on this, we introduce a versatile, hybrid vision transformer backbone called ACC-ViT, tailored for standard vision tasks. Our compact model achieves approximately 84% accuracy on ImageNet-1K with fewer than 28.5 million parameters, outperforming the state-of-the-art MaxViT by 0.42% while requiring 8.4% fewer parameters.