Processing Simple Geometric Attributes with Autoencoders - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Mathematical Imaging and Vision Année : 2020

Processing Simple Geometric Attributes with Autoencoders

Résumé

Image synthesis is a core problem in modern deep learning, and many recent architectures such as autoencoders and Generative Adversarial networks produce spectacular results on highly complex data, such as images of faces or landscapes. While these results open up a wide range of new, advanced synthesis applications, there is also a severe lack of theoretical understanding of how these networks work. This results in a wide range of practical problems, such as difficulties in training, the tendency to sample images with little or no variability, and generalisation problems. In this paper, we propose to analyse the ability of the simplest generative network, the autoencoder, to encode and decode two simple geometric attributes : size and position. We believe that, in order to understand more complicated tasks, it is necessary to first understand how these networks process simple attributes. For the first property, we analyse the case of images of centred disks with variable radii. We explain how the autoencoder projects these images to and from a latent space of smallest possible dimension, a scalar. In particular, we describe a closed-form solution to the decoding training problem in a network without biases, and show that during training, the network indeed finds this solution. We then investigate the best regularisation approaches which yield networks that generalise well. For the second property, position, we look at the encoding and decoding of Dirac delta functions, also known as `one-hot' vectors. We describe a hand-crafted filter that achieves encoding perfectly, and show that the network naturally finds this filter during training. We also show experimentally that the decoding can be achieved if the dataset is sampled in an appropriate manner.
Fichier principal
Vignette du fichier
autoencoders_arxiv_final.pdf (906.27 Ko) Télécharger le fichier
Vignette du fichier
newson2019-thumbnail.pdf (713.67 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02271281 , version 1 (16-11-2020)

Identifiants

Citer

Alasdair Newson, Andrés Almansa, Yann Gousseau, Saïd Ladjal. Processing Simple Geometric Attributes with Autoencoders. Journal of Mathematical Imaging and Vision, 2020, 62 (3), pp.293-312. ⟨10.1007/s10851-019-00924-w⟩. ⟨hal-02271281⟩

Relations

153 Consultations
389 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More