3 papers
cs.CV2025
AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs
Hakan Emre Gedik, Andrew Martin, Mustafa Munir +4
Vision Graph Neural Networks (ViGs) have demonstrated promising performance in image recognition tasks against Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs).…
cs.CV2024
RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone
Mustafa Munir, Md Mostafijur Rahman, Radu Marculescu
Vision transformers (ViTs) have dominated computer vision in recent years. However, ViTs are computationally expensive and not well suited for mobile devices; this led to the preva…
cs.CV2024
Scaling Graph Convolutions for Mobile Vision
William Avery, Mustafa Munir, Radu Marculescu
To compete with existing mobile architectures, MobileViG introduces Sparse Vision Graph Attention (SVGA), a fast token-mixing operator based on the principles of GNNs. However, Mob…