PDE-Driven Spatiotemporal Disentanglement - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

PDE-Driven Spatiotemporal Disentanglement

Résumé

A recent line of work in the machine learning community addresses the problem of predicting high-dimensional spatiotemporal phenomena by leveraging specific tools from the differential equations theory. Following this direction, we propose in this article a novel and general paradigm for this task based on a resolution method for partial differential equations: the separation of variables. This inspiration allows us to introduce a dynamical interpretation of spatiotemporal disentanglement. It induces a principled model based on learning disentangled spatial and temporal representations of a phenomenon to accurately predict future observations. We experimentally demonstrate the performance and broad applicability of our method against prior state-of-the-art models on physical and synthetic video datasets.
Fichier principal
Vignette du fichier
var_sep.pdf (2.12 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02911067 , version 1 (03-08-2020)
hal-02911067 , version 2 (05-10-2020)
hal-02911067 , version 3 (17-03-2021)

Licence

Paternité

Identifiants

Citer

Jérémie Donà, Jean-Yves Franceschi, Sylvain Lamprier, Patrick Gallinari. PDE-Driven Spatiotemporal Disentanglement. 2020. ⟨hal-02911067v2⟩
320 Consultations
142 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More