Variational models for signal processing with Graph Neural Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Variational models for signal processing with Graph Neural Networks

Résumé

This paper is devoted to signal processing on point-clouds by means of neural networks. Nowadays, state-of-the-art in image processing and computer vision is mostly based on training deep convolutional neural networks on large datasets. While it is also the case for the processing of point-clouds with Graph Neural Networks (GNN), the focus has been largely given to high-level tasks such as classification and segmentation using supervised learning on labeled datasets such as ShapeNet. Yet, such datasets are scarce and time-consuming to build depending on the target application. In this work, we investigate the use of variational models for such GNN to process signals on graphs for unsupervised learning. Our contributions are twofold. We first show that some existing variational-based algorithms for signals on graphs can be formulated as Message Passing Networks (MPN), a particular instance of GNN, making them computationally efficient in practice when compared to standard gradient-based machine learning algorithms. Secondly, we investigate the unsupervised learning of feed-forward GNN, either by direct optimization of an inverse problem or by model distillation from variational-based MPN.
Fichier principal
Vignette du fichier
ssvm_paper.pdf (1.54 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03249876 , version 1 (04-06-2021)

Identifiants

  • HAL Id : hal-03249876 , version 1

Citer

Amitoz Azad, Julien Rabin, Abderrahim Elmoataz. Variational models for signal processing with Graph Neural Networks. Scale Space and Variational Methods in Computer Vision, May 2021, Cabourg, France. ⟨hal-03249876⟩
45 Consultations
57 Téléchargements

Partager

Gmail Facebook X LinkedIn More