Part-based approximations for morphological operators using asymmetric auto-encoders - Télécom Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Part-based approximations for morphological operators using asymmetric auto-encoders

Résumé

This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and interpretable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder where the encoder is deep (for accuracy) and the decoder shallow (for interpretability). This method compares favorably to the state-of-the-art online methods on two datasets (MNIST and Fashion MNIST), according to classical metrics and to a new one we introduce, based on the invariance of the representation to morphological dilation.
Fichier principal
Vignette du fichier
non_negative_sparse_autoencoders.pdf (1.23 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02071470 , version 1 (19-03-2019)
hal-02071470 , version 2 (01-04-2019)

Identifiants

Citer

Bastien Ponchon, Santiago Velasco-Forero, Samy Blusseau, Jesus Angulo, Isabelle Bloch. Part-based approximations for morphological operators using asymmetric auto-encoders. International Symposium on Mathematical Morphology, Jul 2019, Saarbrücken, Germany. ⟨hal-02071470v1⟩
4794 Consultations
153 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More