# MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications

arXiv: https://arxiv.org/abs/2307.00395 · HTML: https://mlsanity.com/paper/2307.00395/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 1 Jul 2023.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference](https://mlsanity.com/paper/2104.01136/) (2021)
- [ResMLP: Feedforward networks for image classification with data-efficient training](https://mlsanity.com/paper/2105.03404/) (2021)
- [EfficientFormer: Vision Transformers at MobileNet Speed](https://mlsanity.com/paper/2206.01191/) (2022)
- [Vision GNN: An Image is Worth Graph of Nodes](https://mlsanity.com/paper/2206.00272/) (2022)
- [Separable Self-attention for Mobile Vision Transformers](https://mlsanity.com/paper/2206.02680/) (2022)
- [CycleMLP: A MLP-like Architecture for Dense Prediction](https://mlsanity.com/paper/2107.10224/) (2021)

## Built on by (most cited first, 30 of 35)

- [RepViT: Revisiting Mobile CNN From ViT Perspective](https://mlsanity.com/paper/2307.09283/) (2023)
- [MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training](https://mlsanity.com/paper/2311.17049/) (2023)
- [GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs](https://mlsanity.com/paper/2405.06849/) (2024)
- [Hypergraph Vision Transformers: Images are More than Nodes, More than Edges](https://mlsanity.com/paper/2504.08710/) (2025)
- [Scaling Graph Convolutions for Mobile Vision](https://mlsanity.com/paper/2406.05850/) (2024)
- [WiGNet: Windowed Vision Graph Neural Network](https://mlsanity.com/paper/2410.00807/) (2024)
- [LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones](https://mlsanity.com/paper/2409.03460/) (2024)
- [ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning](https://mlsanity.com/paper/2501.10640/) (2025)
- [VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG](https://mlsanity.com/paper/2311.14775/) (2023)
- [SparseRadNet: Sparse Perception Neural Network on Subsampled Radar Data](https://mlsanity.com/paper/2406.10600/) (2024)
- [CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction](https://mlsanity.com/paper/2411.16170/) (2024)
- [RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization](https://mlsanity.com/paper/2406.16004/) (2024)
- [VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation](https://mlsanity.com/paper/2509.04669/) (2025)
- [RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone](https://mlsanity.com/paper/2412.10995/) (2024)
- [HGFormer: Topology-Aware Vision Transformer with HyperGraph Learning](https://mlsanity.com/paper/2504.02440/) (2025)
- [Vision Graph Prompting via Semantic Low-Rank Decomposition](https://mlsanity.com/paper/2505.04121/) (2025)
- [S2AFormer: Strip Self-Attention for Efficient Vision Transformer](https://mlsanity.com/paper/2505.22195/) (2025)
- [Explaining Vision GNNs: A Semantic and Visual Analysis of Graph-based Image Classification](https://mlsanity.com/paper/2504.19682/) (2025)
- [AdaptViG: Adaptive Vision GNN with Exponential Decay Gating](https://mlsanity.com/paper/2511.09942/) (2025)
- [AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs](https://mlsanity.com/paper/2509.25570/) (2025)
- [Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs](https://mlsanity.com/paper/2510.13740/) (2025)
- [Robust Subgraph Learning by Monitoring Early Training Representations](https://mlsanity.com/paper/2403.09901/) (2024)
- [OneNet: A Channel-Wise 1D Convolutional U-Net](https://mlsanity.com/paper/2411.09838/) (2024)
- [RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations](https://mlsanity.com/paper/2412.19628/) (2024)
- [i-WiViG: Interpretable Window Vision GNN](https://mlsanity.com/paper/2503.08321/) (2025)
- [Talk2PC: Enhancing 3D Visual Grounding through LiDAR and Radar Point Clouds Fusion for Autonomous Driving](https://mlsanity.com/paper/2503.08336/) (2025)
- [Cognitively-Inspired Emergent Communication via Knowledge Graphs for Assisting the Visually Impaired](https://mlsanity.com/paper/2505.22087/) (2025)
- [ViG-LRGC: Vision Graph Neural Networks with Learnable Reparameterized Graph Construction](https://mlsanity.com/paper/2509.18840/) (2025)
- [Patch as Node: Human-Centric Graph Representation Learning for Multimodal Action Recognition](https://mlsanity.com/paper/2512.21916/) (2025)
- [Human-inspired Global-to-Parallel Multi-scale Encoding for Lightweight Vision Models](https://mlsanity.com/paper/2601.08190/) (2026)

## Abstract (arXiv)

Traditionally, convolutional neural networks (CNN) and vision transformers (ViT) have dominated computer vision. However, recently proposed vision graph neural networks (ViG) provide a new avenue for exploration. Unfortunately, for mobile applications, ViGs are computationally expensive due to the overhead of representing images as graph structures. In this work, we propose a new graph-based sparse attention mechanism, Sparse Vision Graph Attention (SVGA), that is designed for ViGs running on mobile devices. Additionally, we propose the first hybrid CNN-GNN architecture for vision tasks on mobile devices, MobileViG, which uses SVGA. Extensive experiments show that MobileViG beats existing ViG models and existing mobile CNN and ViT architectures in terms of accuracy and/or speed on image classification, object detection, and instance segmentation tasks. Our fastest model, MobileViG-Ti, achieves 75.7% top-1 accuracy on ImageNet-1K with 0.78 ms inference latency on iPhone 13 Mini NPU (compiled with CoreML), which is faster than MobileNetV2x1.4 (1.02 ms, 74.7% top-1) and MobileNetV2x1.0 (0.81 ms, 71.8% top-1). Our largest model, MobileViG-B obtains 82.6% top-1 accuracy with only 2.30 ms latency, which is faster and more accurate than the similarly sized EfficientFormer-L3 model (2.77 ms, 82.4%). Our work proves that well designed hybrid CNN-GNN architectures can be a new avenue of exploration for designing models that are extremely fast and accurate on mobile devices. Our code is publicly available at https://github.com/SLDGroup/MobileViG.