# No Routing Needed Between Capsules

arXiv: https://arxiv.org/abs/2001.09136 · HTML: https://mlsanity.com/paper/2001.09136/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2020.

## Built on by (most cited first, 27 of 27)

- [The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning](https://mlsanity.com/paper/2402.01889/) (2024)
- [Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM](https://mlsanity.com/paper/2207.10226/) (2022)
- [Evaluating Bayes Error Estimators on Real-World Datasets with FeeBee](https://mlsanity.com/paper/2108.13034/) (2021)
- [Gaussian Process Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2407.18397/) (2024)
- [XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks](https://mlsanity.com/paper/2111.10854/) (2021)
- [Laplace-HDC: Understanding the geometry of binary hyperdimensional computing](https://mlsanity.com/paper/2404.10759/) (2024)
- [Dataset Distillation in Medical Imaging: A Feasibility Study](https://mlsanity.com/paper/2407.14429/) (2024)
- [Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices](https://mlsanity.com/paper/2108.06128/) (2021)
- [Towards an Analytical Definition of Sufficient Data](https://mlsanity.com/paper/2202.03238/) (2022)
- [Handwritten Arabic Character Recognition for Children Writ-ing Using Convolutional Neural Network and Stroke Identification](https://mlsanity.com/paper/2211.02119/) (2022)
- [Hybridization of Capsule and LSTM Networks for unsupervised anomaly detection on multivariate data](https://mlsanity.com/paper/2202.05538/) (2022)
- [Learning in Wilson-Cowan model for metapopulation](https://mlsanity.com/paper/2406.16453/) (2024)
- [Direct domain adaptation through reciprocal linear transformations](https://mlsanity.com/paper/2108.07600/) (2021)
- [Class Density and Dataset Quality in High-Dimensional, Unstructured Data](https://mlsanity.com/paper/2202.03856/) (2022)
- [On when is Reservoir Computing with Cellular Automata Beneficial?](https://mlsanity.com/paper/2407.09501/) (2024)
- [A New Quantum CNN Model for Image Classification](https://mlsanity.com/paper/2203.11155/) (2022)
- [Maintaining Performance with Less Data](https://mlsanity.com/paper/2208.02007/) (2022)
- [MindBigData 2023 MNIST-8B The 8 billion datapoints Multimodal Dataset of Brain Signals](https://mlsanity.com/paper/2306.00455/) (2023)
- [Pruning Distorted Images in MNIST Handwritten Digits](https://mlsanity.com/paper/2307.14343/) (2023)
- [Classification of Non-native Handwritten Characters Using Convolutional Neural Network](https://mlsanity.com/paper/2406.04511/) (2024)
- [On Diversity in Discriminative Neural Networks](https://mlsanity.com/paper/2407.12599/) (2024)
- [Deep Trees for (Un)structured Data: Tractability, Performance, and Interpretability](https://mlsanity.com/paper/2410.21595/) (2024)
- [Towards Seamless Hierarchical Federated Learning under Intermittent Client Participation: A Stagewise Decision-Making Methodology](https://mlsanity.com/paper/2502.09303/) (2025)
- [Single-Qudit Quantum Neural Networks for Multiclass Classification](https://mlsanity.com/paper/2503.09269/) (2025)
- [Realistic Handwritten Multi-Digit Writer (MDW) Number Recognition Challenges](https://mlsanity.com/paper/2512.00676/) (2025)
- [A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks](https://mlsanity.com/paper/2603.22987/) (2026)
- [QSV: Quat-Sphere-Vision for Coupled Quaternion Attention on Spherical Lattices](https://mlsanity.com/paper/2609.30592/) (2026)

## Abstract (arXiv)

Most capsule network designs rely on traditional matrix multiplication between capsule layers and computationally expensive routing mechanisms to deal with the capsule dimensional entanglement that the matrix multiplication introduces. By using Homogeneous Vector Capsules (HVCs), which use element-wise multiplication rather than matrix multiplication, the dimensions of the capsules remain unentangled. In this work, we study HVCs as applied to the highly structured MNIST dataset in order to produce a direct comparison to the capsule research direction of Geoffrey Hinton, et al. In our study, we show that a simple convolutional neural network using HVCs performs as well as the prior best performing capsule network on MNIST using 5.5x fewer parameters, 4x fewer training epochs, no reconstruction sub-network, and requiring no routing mechanism. The addition of multiple classification branches to the network establishes a new state of the art for the MNIST dataset with an accuracy of 99.87% for an ensemble of these models, as well as establishing a new state of the art for a single model (99.83% accurate).