An Algorithm for Routing Capsules in All Domains

2 Nov 2019  ·  Franz A. Heinsen ·

Building on recent work on capsule networks, we propose a new, general-purpose form of "routing by agreement" that activates output capsules in a layer as a function of their net benefit to use and net cost to ignore input capsules from earlier layers. To illustrate the usefulness of our routing algorithm, we present two capsule networks that apply it in different domains: vision and language. The first network achieves new state-of-the-art accuracy of 99.1% on the smallNORB visual recognition task with fewer parameters and an order of magnitude less training than previous capsule models, and we find evidence that it learns to perform a form of "reverse graphics." The second network achieves new state-of-the-art accuracies on the root sentences of the Stanford Sentiment Treebank: 58.5% on fine-grained and 95.6% on binary labels with a single-task model that routes frozen embeddings from a pretrained transformer as capsules. In both domains, we train with the same regime. Code is available at along with replication instructions.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Image Classification smallNORB Heinsen Routing Classification Error 0.90 # 1
Sentiment Analysis SST-2 Binary classification Heinsen Routing + GPT-2 Accuracy 95.6 # 21
Sentiment Analysis SST-5 Fine-grained classification Heinsen Routing + GPT-2 Accuracy 58.5 # 3