Dynamic Filters in Graph Convolutional Networks

Nitika Verma 1, 2 Edmond Boyer 1 Jakob Verbeek 2
1 MORPHEO - Capture and Analysis of Shapes in Motion
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
Abstract : 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.
Type de document :
Pré-publication, Document de travail
Liste complète des métadonnées

Littérature citée [27 références]  Voir  Masquer  Télécharger

Contributeur : Thoth Team <>
Soumis le : vendredi 16 juin 2017 - 17:02:50
Dernière modification le : jeudi 11 janvier 2018 - 06:27:41
Document(s) archivé(s) le : mardi 12 décembre 2017 - 19:21:36


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01540389, version 1
  • ARXIV : 1706.05206


Nitika Verma, Edmond Boyer, Jakob Verbeek. Dynamic Filters in Graph Convolutional Networks. 2017. 〈hal-01540389〉



Consultations de la notice


Téléchargements de fichiers