PCA-AE: Principal Component Analysis Autoencoder for Organising the Latent Space of Generative Networks - Département Image, Données, Signal Accéder directement au contenu
Article Dans Une Revue Journal of Mathematical Imaging and Vision Année : 2022

PCA-AE: Principal Component Analysis Autoencoder for Organising the Latent Space of Generative Networks

Résumé

Autoencoders and generative models produce some of the most spectacular deep learning results to date. However, understanding and controlling the latent space of these models presents a considerable challenge. Drawing inspiration from principal component analysis and autoencoders, we propose the Principal Component Analysis Autoencoder (PCA-AE). This is a novel autoencoder whose latent space verifies two properties. Firstly, the dimensions are organised in decreasing importance with respect to the data at hand. Secondly, the components of the latent space are statistically independent. We achieve this by progressively increasing the latent space during training, and with a covariance loss applied to the latent codes. The resulting autoencoder produces a latent space which separates the intrinsic attributes of the data into different components of the latent space, in a completely unsupervised manner. We also describe an extension of our approach to the case of powerful, pre-trained GANs. We show results on both synthetic examples of shapes and on a state-of-the-art GAN. For example, we are able to separate the colour shade scale of hair, pose of faces and gender, without accessing any labels. We compare the PCA-AE with
Fichier principal
Vignette du fichier
JMIV_majorRevision.pdf (51.64 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03713275 , version 1 (04-07-2022)

Identifiants

Citer

Chi-Hieu Pham, Saïd Ladjal, Alasdair Newson. PCA-AE: Principal Component Analysis Autoencoder for Organising the Latent Space of Generative Networks. Journal of Mathematical Imaging and Vision, 2022, 64 (5), pp.569-585. ⟨10.1007/s10851-022-01077-z⟩. ⟨hal-03713275⟩
332 Consultations
12 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More