Domain Translation via Latent Space Mapping - Normandie Université Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Domain Translation via Latent Space Mapping

Résumé

In this paper, we study the problem of multi-domain translation: given an element (a) of domain A, we wish to generate a corresponding element (b) in another domain B, and vice versa. Acquiring supervision in multiple domains can be a tedious task, also we propose to learn this translation from one domain to another when supervision is available as a pair (a, b), and leverage possible unpaired data when only (a) or only (b) is available. We introduce a new unified framework called Latent Space Mapping (LSM), which exploits the manifold assumption to learn a latent space from each domain. Unlike existing approaches, we propose to further regularize each latent space using available domains by learning each dependency between pairs of domains. We evaluate our approach on three tasks performing i) a synthetic dataset with image translation, ii) a real-world task of semantic segmentation for medical images, and iii) a real-world task of facial landmark detection.
Fichier principal
Vignette du fichier
2212.03361.pdf (2.65 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04461418 , version 1 (16-02-2024)

Identifiants

Citer

Tsiry Mayet, Simon Bernard, Clement Chatelain, Romain Hérault. Domain Translation via Latent Space Mapping. 2023 International Joint Conference on Neural Networks (IJCNN), Jun 2023, Gold Coast, Australia. pp.1-10, ⟨10.1109/IJCNN54540.2023.10191215⟩. ⟨hal-04461418⟩
24 Consultations
6 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More