Capsules with Inverted Dot-Product Attention Routing

By Yao-Hung Hubert Tsai, Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov. 2020

93 citations recorded by the source corpus.

We introduce a new routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement between the parent's state and the child's vote. The new mechanism 1) designs routing via inverted dot-product attention; 2) imposes Layer Normalization as normalization; and 3) replaces sequential iterative routing with concurrent iterative routing. When compared to previously proposed routing algorithms, our method improves performance on benchmark datasets such as CIFAR-10 and CIFAR-100, and it performs at-par with a powerful CNN (ResNet-18) with 4x fewer parameters. On a different task of recognizing digits from overlayed digit images, the proposed capsule model performs favorably against CNNs given the same number of layers and neurons per layer. We believe that our work raises the possibility of applying capsule networks to complex real-world tasks. Our code is publicly available at: this https URL An alternative implementation is available at: this https URL

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Model Architectures

Citations in the corpus

Object-Centric Learning with Slot Attention (2020, methodology): “[62] Yao-Hung Hubert Tsai, Nitish Srivastava, Hanlin Goh, and Ruslan Salakhutdinov.”