WiGNet: Windowed Vision Graph Neural Network

TL;DR

WiGNet introduces a windowed graph neural network approach for efficient image processing, reducing computational complexity while maintaining competitive accuracy on large-scale vision benchmarks.

Contribution

The paper proposes a novel windowed graph neural network architecture that partitions images into windows, enabling scalable and efficient vision GNNs for large images.

Findings

Achieves competitive accuracy on ImageNet-1k.

Reduces computational and memory complexity.

Demonstrates effectiveness on high-resolution CelebA-HQ images.

Abstract

In recent years, Graph Neural Networks (GNNs) have demonstrated strong adaptability to various real-world challenges, with architectures such as Vision GNN (ViG) achieving state-of-the-art performance in several computer vision tasks. However, their practical applicability is hindered by the computational complexity of constructing the graph, which scales quadratically with the image size. In this paper, we introduce a novel Windowed vision Graph neural Network (WiGNet) model for efficient image processing. WiGNet explores a different strategy from previous works by partitioning the image into windows and constructing a graph within each window. Therefore, our model uses graph convolutions instead of the typical 2D convolution or self-attention mechanism. WiGNet effectively manages computational and memory complexity for large image sizes. We evaluate our method in the ImageNet-1k benchmark dataset and test the adaptability of WiGNet using the CelebA-HQ dataset as a downstream task with higher-resolution images. In both of these scenarios, our method achieves competitive results compared to previous vision GNNs while keeping memory and computational complexity at bay. WiGNet offers a promising solution toward the deployment of vision GNNs in real-world applications. We publicly released the code at https://github.com/EIDOSLAB/WiGNet.