Unifying local and non-local signal processing with graph CNNs
arXiv:1702.07759
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.
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Semi-Supervised Classification with Graph Convolutional Networks
- Geometric deep learning: going beyond Euclidean data
- Deep Convolutional Networks on Graph-Structured Data
- A Powerful Generative Model Using Random Weights for the Deep Image Representation
- Texture Synthesis Using Shallow Convolutional Networks with Random Filters
Cited by in corpus (6)
- Audio style transfer
- Stability and Generalization of Graph Convolutional Neural Networks
- Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning
- Decentralized Inference with Graph Neural Networks in Wireless Communication Systems
- Fast Spectral Ranking for Similarity Search
- Generalization bounds for graph convolutional neural networks via Rademacher complexity