Vision graph neural networks (ViG) offer a new avenue for exploration in
computer vision. A major bottleneck in ViGs is the inefficient k-nearest
neighbor (KNN) operation used for graph construction. To solve this issue, we
propose a new method for designing ViGs, Dynamic Axial Graph Construction
(DAGC), which is more efficient than KNN as it limits the number of considered
graph connections made within an image. Additionally, we propose a novel
CNN-GNN architecture, GreedyViG, which uses DAGC. Extensive experiments show
that GreedyViG beats existing ViG, CNN, and ViT architectures in terms of
accuracy, GMACs, and parameters on image classification, object detection,
instance segmentation, and semantic segmentation tasks. Our smallest model,
GreedyViG-S, achieves 81.1% top-1 accuracy on ImageNet-1K, 2.9% higher than
Vision GNN and 2.2% higher than Vision HyperGraph Neural Network (ViHGNN), with
less GMACs and a similar number of parameters. Our largest model, GreedyViG-B
obtains 83.9% top-1 accuracy, 0.2% higher than Vision GNN, with a 66.6%
decrease in parameters and a 69% decrease in GMACs. GreedyViG-B also obtains
the same accuracy as ViHGNN with a 67.3% decrease in parameters and a 71.3%
decrease in GMACs. Our work shows that hybrid CNN-GNN architectures not only
provide a new avenue for designing efficient models, but that they can also
exceed the performance of current state-of-the-art models.

利用动态轴图构建（DAGC）和 GreedyViG 的混合 CNN-GNN 架构，在图像分类等任务中实现了高精度，GMACs 减少，参数数量相似的效果，超过了现有的视觉图神经网络模型。

GreedyViG：用于高效视觉 GNN 的动态轴图构建

GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs

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 this https URL

本文提出了一种新颖的基于图的稀疏注意力机制 Sparse Vision Graph Attention（SVGA），并且设计了一种新的混合 CNN-GNN 体系结构 MobileViG，实验证明，MobileViG 在移动设备上进行图像分类、物体检测和实例分割任务上的精度和 / 或速度明显优于现有的 ViG 模型和现有移动 CNN 和 ViT 架构。