Communication Dans Un Congrès Année : 2023

Disentangled latent representations of images with atomic autoencoders

Résumé

We present the atomic autoencoder architecture, which decomposes an image as the sum of elementary parts that are parametrized by simple separate blocks of latent codes. We show that this simple architecture is induced by the definition of a general atomic low-dimensional model of the considered data. We also highlight the fact that the atomic autoencoder achieves disentangled low-dimensional representations under minimal hypotheses. Experiments show that their implementation with deep neural networks is successful at learning disentangled representations on two different examples: images constructed with simple parametric curves and images of filtered off-the-grid spikes.

Fichier principal
Vignette du fichier
atomic_autoencoders_hal2.pdf (351.42 Ko) Télécharger le fichier
atomic_autoencoders_hal2_supp_mat.pdf (351.19 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03962759 , version 1 (30-01-2023)
hal-03962759 , version 2 (22-05-2023)

Licence

Identifiants

  • HAL Id : hal-03962759 , version 2

Citer

Alasdair Newson, Yann Traonmilin. Disentangled latent representations of images with atomic autoencoders. Sampling Theory and Applications Conference, Jul 2023, Sampling Theory and Applications Conference, United States. ⟨hal-03962759v2⟩
688 Consultations
512 Téléchargements

Partager

  • More