Unifying local and non-local signal processing with graph CNNs

Gilles Puy; Srdan Kitic; Patrick Pérez

Unifying local and non-local signal processing with graph CNNs

Computer Vision and Pattern Recognition 2017-07-10 v2

Authors: Gilles Puy , Srdan Kitic , Patrick Pérez

Abstract

This paper deals with the unification of local and non-local signal processing on graphs within a single convolutional neural network (CNN) framework. Building upon recent works on graph CNNs, we propose to use convolutional layers that take as inputs two variables, a signal and a graph, allowing the network to adapt to changes in the graph structure. In this article, we explain how this framework allows us to design a novel method to perform style transfer.

Keywords

graph convolutional network convolutional neural network graph neural network

Cite

@article{arxiv.1702.07759,
  title  = {Unifying local and non-local signal processing with graph CNNs},
  author = {Gilles Puy and Srdan Kitic and Patrick Pérez},
  journal= {arXiv preprint arXiv:1702.07759},
  year   = {2017}
}

Related papers

View all related →

Signal Processing · Electrical Eng. & Systems

Convolutional Neural Network Architectures for Signals Supported on Graphs

Fernando Gama, Antonio G. Marques, Geert Leus, Alejandro Ribeiro