Disentangled latent representations of images with atomic autoencoders - Département Image, Données, Signal Access content directly
Preprints, Working Papers, ... Year : 2023

Disentangled latent representations of images with atomic autoencoders

Abstract

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 denition of a general 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 dierent examples: images constructed with simple parametric curves and images of ltered o-the-grid spikes.
Fichier principal
Vignette du fichier
atomic_autoencoders_hal.pdf (439.61 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

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

Identifiers

  • HAL Id : hal-03962759 , version 1

Cite

Alasdair Newson, Yann Traonmilin. Disentangled latent representations of images with atomic autoencoders. 2023. ⟨hal-03962759v1⟩

Collections

INSMI
303 View
91 Download

Share

Gmail Facebook X LinkedIn More