Afficher la couverture 'Part-based approximations for morphological operators using asymmetric auto-encoders | Ponchon, Bastien' en grand format
/5

0 avis

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

Archive ouverte

Ponchon, Bastien | Velasco-Forero, Santiago | Blusseau, Samy | Angulo, Jesus | Bloch, Isabelle

Edité par CCSD -

International audience. 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.

Suggestions

Du même auteur

Max-plus Operators Applied to Filter Selection and Model Pruning in Neural Networks

Archive ouverte | Zhang, Yunxiang | CCSD

International audience. Following recent advances in morphological neural networks, we propose to study in more depth how Max-plus operators can be exploited to define morphological units and how they behave when in...

Scale Equivariant Neural Networks with Morphological Scale-Spaces

Archive ouverte | Sangalli, Mateus | CCSD

International audience. The translation equivariance of convolutions can make convolutional neural networks translation equivariant or invariant. Equivariance to other transformations (e.g. rotations, affine transf...

Moving Frame Net: SE(3)-Equivariant Network for Volumes

Archive ouverte | Sangalli, Mateus | CCSD

International audience. Equivariance of neural networks to transformations helps to improve their performance and reduce generalization error in computer vision tasks, as they apply to datasets presenting symmetries...

Chargement des enrichissements...