PDE-Driven Spatiotemporal Disentanglement - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Poster De Conférence Année : 2021

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_poster.pdf (528.87 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03181039 , version 1 (25-03-2021)

Licence

Paternité

Identifiants

  • HAL Id : hal-03181039 , version 1

Citer

Jérémie Donà, Jean-Yves Franceschi, Sylvain Lamprier, Patrick Gallinari. PDE-Driven Spatiotemporal Disentanglement. The Ninth International Conference on Learning Representations, May 2021, Vienne (virtual), Austria. . ⟨hal-03181039⟩
81 Consultations
29 Téléchargements

Partager

Gmail Facebook X LinkedIn More