# PDR-CapsNet: an Energy-Efficient Parallel Approach to Dynamic Routing in Capsule Networks

arXiv: https://arxiv.org/abs/2310.03212 · HTML: https://mlsanity.com/paper/2310.03212/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 15 references that are in the map.
- First posted on arXiv 4 Oct 2023.

## Builds on (most cited first, 8 of 8)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [HitNet: a neural network with capsules embedded in a Hit-or-Miss layer, extended with hybrid data augmentation and ghost capsules](https://mlsanity.com/paper/1806.06519/) (2018)
- [Dense and Diverse Capsule Networks: Making the Capsules Learn Better](https://mlsanity.com/paper/1805.04001/) (2018)
- [The Multi-Lane Capsule Network (MLCN)](https://mlsanity.com/paper/1902.08431/) (2019)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have produced state-of-the-art results for image classification tasks. However, they are limited in their ability to handle rotational and viewpoint variations due to information loss in max-pooling layers. Capsule Networks (CapsNets) employ a computationally-expensive iterative process referred to as dynamic routing to address these issues. CapsNets, however, often fall short on complex datasets and require more computational resources than CNNs. To overcome these challenges, we introduce the Parallel Dynamic Routing CapsNet (PDR-CapsNet), a deeper and more energy-efficient alternative to CapsNet that offers superior performance, less energy consumption, and lower overfitting rates. By leveraging a parallelization strategy, PDR-CapsNet mitigates the computational complexity of CapsNet and increases throughput, efficiently using hardware resources. As a result, we achieve 83.55% accuracy while requiring 87.26% fewer parameters, 32.27% and 47.40% fewer MACs, and Flops, achieving 3x faster inference and 7.29J less energy consumption on a 2080Ti GPU with 11GB VRAM compared to CapsNet and for the CIFAR-10 dataset.