Disentangled latent representations of images with atomic autoencoders
| hal.structure.identifier | Laboratoire Traitement et Communication de l'Information [LTCI] | |
| hal.structure.identifier | Département Images, Données, Signal [IDS] | |
| hal.structure.identifier | Image, Modélisation, Analyse, GEométrie, Synthèse [IMAGES] | |
| dc.contributor.author | NEWSON, Alasdair | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | TRAONMILIN, Yann | |
| dc.date.accessioned | 2024-04-04T02:34:16Z | |
| dc.date.available | 2024-04-04T02:34:16Z | |
| dc.date.issued | 2023 | |
| dc.date.conference | 2023-07-10 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/190538 | |
| dc.description.abstractEn | 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. | |
| dc.description.sponsorship | Régularisation performante de problèmes inverses en grande dimension pour le traitement de données - ANR-20-CE40-0001 | |
| dc.description.sponsorship | Édition d'imgage avec des réseaux génératifs profonds - ANR-21-CE23-0024 | |
| dc.language.iso | en | |
| dc.subject.en | low dimensional models | |
| dc.subject.en | autoencoders | |
| dc.subject.en | disentanglement | |
| dc.title.en | Disentangled latent representations of images with atomic autoencoders | |
| dc.type | Communication dans un congrès | |
| dc.subject.hal | Informatique [cs]/Traitement des images | |
| dc.subject.hal | Informatique [cs]/Réseau de neurones [cs.NE] | |
| dc.subject.hal | Statistiques [stat] | |
| bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.conference.title | Sampling Theory and Applications Conference | |
| bordeaux.country | US | |
| bordeaux.conference.city | Sampling Theory and Applications Conference | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-03962759 | |
| hal.version | 1 | |
| hal.invited | non | |
| hal.proceedings | non | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-03962759v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2023&rft.au=NEWSON,%20Alasdair&TRAONMILIN,%20Yann&rft.genre=unknown |
Files in this item
| Files | Size | Format | View |
|---|---|---|---|
|
There are no files associated with this item. |
|||