Learning Disentangled Representations via Mutual Information Estimation - Université Toulouse 3 Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Learning Disentangled Representations via Mutual Information Estimation

Résumé

In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representation which is split into two parts: a shared representation that captures the common information between the images and an exclusive representation that contains the specific information of each image. To address this issue, we propose a model based on mutual information estimation without relying on image reconstruction or image generation. Mutual information maximization is performed to capture the attributes of data in the shared and exclusive representations while we minimize the mutual information between the shared and exclusive representation to enforce representation disentanglement. We show that these representations are useful to perform downstream tasks such as image classification and image retrieval based on the shared or exclusive component. Moreover, classification results show that our model outperforms the state-of-the-art model based on VAE/GAN approaches in representation disentanglement.
Fichier principal
Vignette du fichier
main.pdf (2.6 Mo) Télécharger le fichier

Dates et versions

hal-02397803 , version 1 (06-12-2019)

Identifiants

Citer

Eduardo Hugo Sanchez, Mathieu Serrurier, Mathias Ortner. Learning Disentangled Representations via Mutual Information Estimation. 16th European Conference on Computer Vision - ECCV 2020, Aug 2020, online, France. pp.205-221, ⟨10.1007/978-3-030-58542-6_13⟩. ⟨hal-02397803⟩
260 Consultations
356 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More