Capsule networks as recurrent models of grouping and segmentation

HIGHLIGHTS

• who: Adrien Doerig and collaborators from the Computer Science, Technische Universität Berlin, Berlin, Germany, Institute of Psychology, University of have published the Article: Capsule networks as recurrent models of grouping and segmentation, in the Journal: (JOURNAL) of November/26,/2019
• what: The authors show that Capsule Neural Networks (CapsNets) combining ffCNNs with recurrent grouping and segmentation solve this challenge. The authors provide psychophysical evidence that grouping and segmentation are implemented recurrently in humans and show that CapsNets reproduce these results well. Together the authors provide mutually reinforcing psychophysical and computational evidence that a recurrent . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.