Dynamic Filters in Graph Convolutional Networks

By Nitika Verma, Edmond Boyer, Jakob Verbeek. 2017

26 citations recorded by the source corpus.

Convolutional neural networks (CNNs) have massively impacted visual recognition in 2D images, and are now ubiquitous in state-of-the-art approaches. While CNNs naturally extend to other domains, such as audio and video, where data is also organized in rectangular grids, they do not easily generalize to other types of data such as 3D shape meshes, social network graphs or molecular graphs. To handle such data, we propose a novel graph-convolutional network architecture that builds on a generic formulation that relaxes the 1-to-1 correspondence between filter weights and data elements around the center of the convolution. The main novelty of our architecture is that the shape of the filter is a function of the features in the previous network layer, which is learned as an integral part of the neural network. Experimental evaluations on digit recognition, semi-supervised document classification, and 3D shape correspondence yield state-of-the-art results, significantly improving over previous work for shape correspondence.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Generating 3D faces using Convolutional Mesh Autoencoders (2018, background): “[45] presente dynamic filtering on graphs where the filter weights depend on the inputs.”
Attention-based Graph Neural Network for Semi-supervised Learning (2018, methodology): “The classiﬁcation accuracy of all the baseline methods are collected from [46, 27, 38, 31, 11, 41].”
Deformable Shape Completion with Graph Convolutional Autoencoders (2017, methodology): “Refer to Figure 1 and [56] for further details.”