Accéder directement au contenu Accéder directement à la navigation
Article dans une revue

Capsule networks as recurrent models of grouping and segmentation

Abstract : Classically, visual processing is described as a cascade of local feedforward computations. Feedforward Convolutional Neural Networks (ffCNNs) have shown how powerful such models can be. However, using visual crowding as a well-controlled challenge, we previously showed that no classic model of vision, including ffCNNs, can explain human global shape processing. Here, we show that Capsule Neural Networks (CapsNets), combining ffCNNs with recurrent grouping and segmentation, solve this challenge. We also show that ffCNNs and standard recurrent CNNs do not, suggesting that the grouping and segmentation capabilities of CapsNets are crucial. Furthermore, we provide psychophysical evidence that grouping and segmentation are implemented recurrently in humans, and show that CapsNets reproduce these results well. We discuss why recurrence seems needed to implement grouping and segmentation efficiently. Together, we provide mutually reinforcing psychophysical and computational evidence that a recurrent grouping and segmentation process is essential to understand the visual system and create better models that harness global shape computations.
Type de document :
Article dans une revue
Liste complète des métadonnées

https://hal.univ-lille.fr/hal-03095372
Contributeur : Lilloa Université de Lille <>
Soumis le : lundi 4 janvier 2021 - 16:03:53
Dernière modification le : samedi 16 janvier 2021 - 03:19:59
Archivage à long terme le : : lundi 5 avril 2021 - 20:51:58

Fichier

Doerig 2020 PlosCompBio.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Collections

Citation

Adrien Doerig, Lynn Schmittwilken, Bilge Sayim, Mauro Manassi, Michael H Herzog. Capsule networks as recurrent models of grouping and segmentation. PLoS Computational Biology, Public Library of Science, 2020, PLoS Computational Biology, 16, pp.e1008017. ⟨10.1371/journal.pcbi.1008017⟩. ⟨hal-03095372⟩

Partager

Métriques

Consultations de la notice

16

Téléchargements de fichiers

29