Disentangling high-level factors and their features with Conditional Vector Quantized VAEs - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Letters Année : 2023

Disentangling high-level factors and their features with Conditional Vector Quantized VAEs

Résumé

Two recent works have shown the benefit of modeling both high-level factors and their related features to learn disentangled representations with variational autoencoders (VAE). We propose here a novel VAE-based approach that follows this principle. Inspired by conditional VAE, the features are no longer treated as random variables over which integration must be performed. Instead, they are deterministically computed from the input data using a neural network whose parameters can be estimated jointly with those of the decoder and of the encoder. Moreover, the quality of the generated images has been improved by using discrete latent variables and a two-step learning procedure, which makes it possible to increase the size of the latent space without altering the disentanglement properties of the model. Results obtained on two different datasets validate the proposed approach that achieves better performance than the two aforementioned works in terms of disentanglement, while providing higher quality images.
Fichier principal
Vignette du fichier
Zou2023PRL.pdf (3.71 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04121549 , version 1 (08-09-2023)

Identifiants

Citer

Kaifeng Zou, Sylvain Faisan, Fabrice Heitz, Sébastien Valette. Disentangling high-level factors and their features with Conditional Vector Quantized VAEs. Pattern Recognition Letters, 2023, 172, pp.172-180. ⟨10.1016/j.patrec.2023.05.028⟩. ⟨hal-04121549⟩
36 Consultations
54 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More