Unsupervised multiple domain translation through controlled Disentanglement in variational autoencoder - LIUM - Equipe Language and Speech Technology Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Unsupervised multiple domain translation through controlled Disentanglement in variational autoencoder

Résumé

Unsupervised Multiple Domain Translation is the task of transforming data from one domain to other domains without having paired data to train the systems. Typically, methods based on Generative Adversarial Networks (GANs) are used to address this task. However, our proposal exclusively relies on a modified version of a Variational Autoencoder. This modification consists of the use of two latent variables disentangled in a controlled way by design. One of this latent variables is imposed to depend exclusively on the domain, while the other one must depend on the rest of the variability factors of the data. Additionally, the conditions imposed over the domain latent variable allow for better control and understanding of the latent space. We empirically demonstrate that our approach works on different vision datasets improving the performance of other well known methods. Finally, we prove that, indeed, one of the latent variables stores all the information related to the domain and the other one hardly contains any domain information.
Fichier principal
Vignette du fichier
ICASSP_2024_var_translation_vf.pdf (1.23 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04638710 , version 1 (08-07-2024)

Identifiants

Citer

Antonio Almudévar, Théo Mariotte, Alfonso Ortega, Marie Tahon. Unsupervised multiple domain translation through controlled Disentanglement in variational autoencoder. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2024, Seoul, France. pp.7010-7014, ⟨10.1109/ICASSP48485.2024.10446649⟩. ⟨hal-04638710⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More