arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.06307cs.LGcs.AIcs.CV
收藏

基于图像的图神经网络综述

Survey of Image Based Graph Neural Networks

Usman Nazir, He Wang, Murtaza Taj

摘要:

在这篇综述论文中,我们分析了基于图像的图神经网络,并提出了一个三步分类方法。我们首先使用Quickshift算法将图像转换为超像素,以便减少30%的输入数据。超像素随后用于生成区域邻接图。最后,将图通过最先进的图卷积神经网络以获得分类分数。我们还分析了图神经网络中的空间卷积滤波技术和谱卷积滤波技术。基于光谱的模型比基于空间的模型和经典的CNN性能更好,计算成本更低。

英文摘要:

In this survey paper, we analyze image based graph neural networks and propose a three-step classification approach. We first convert the image into superpixels using the Quickshift algorithm so as to reduce 30% of the input data. The superpixels are subsequently used to generate a region adjacency graph. Finally, the graph is passed through a state-of-art graph convolutional neural network to get classification scores. We also analyze the spatial and spectral convolution filtering techniques in graph neural networks. Spectral-based models perform better than spatial-based models and classical CNN with lesser compute cost.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑