An Optimization View on Dynamic Routing Between Capsules

129 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Stacked Capsule Autoencoders (2019, background): “Iterative routing is inefﬁcient and has prompted further research (Wang and Liu, 2018; Zhang et al., 2018; Li et al., 2018).”
Neural Network Encapsulation (2018, background): “[21] formulated the routing process as an optimization problem that minimizes the clustering-like loss and a KL regularization term.”
Building Deep, Equivariant Capsule Networks (2019, background): “s exist, for example dynamic routing =((Sabour et al., 2017)), EM-routing =((Hinton et al., 2018)), SVD-based routing =((Bahadori, 2018)), and routing based on a clustering-like objective function =((Wang and Liu, 2018)). These are based on differing notions of consensus, and consequently affect the”
Capsules with Inverted Dot-Product Attention Routing (2020, methodology): “Wang & Liu (2018) formulated the Dynamic routing (Sabour et al., 2017) as an optimization problem consisting of a clustering loss and a KL regularization term.”
3D Point Capsule Networks (2018, background): “Wang and Liu saw the routing as an optimization minimizing a combination of clustering-like loss and a KL regularization term [36].”