Capsule networks as recurrent models of grouping and segmentation - Université de Lille Accéder directement au contenu
Article Dans Une Revue PLoS Computational Biology Année : 2020

Capsule networks as recurrent models of grouping and segmentation


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.
Fichier principal
Vignette du fichier
Doerig 2020 PlosCompBio.pdf (2.59 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03095372 , version 1 (04-01-2021)




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



Gmail Mastodon Facebook X LinkedIn More