Skip to Main content Skip to Navigation
New interface
Journal articles

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

Abstract : 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
Complete list of metadata
Contributor : Chi-Hieu Pham Connect in order to contact the contributor
Submitted on : Monday, July 4, 2022 - 3:25:20 PM
Last modification on : Thursday, July 14, 2022 - 3:52:58 AM


Files produced by the author(s)



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⟩



Record views


Files downloads