# PrunedCaps: A Case For Primary Capsules Discrimination

arXiv: https://arxiv.org/abs/2512.06003 · HTML: https://mlsanity.com/paper/2512.06003/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 2 Dec 2025.

## Builds on (most cited first, 10 of 10)

- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [The State of Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1902.09574/) (2019)
- [NISP: Pruning Networks using Neuron Importance Score Propagation](https://mlsanity.com/paper/1711.05908/) (2017)
- [Accelerating Very Deep Convolutional Networks for Classification and Detection](https://mlsanity.com/paper/1505.06798/) (2015)
- [A Signal Propagation Perspective for Pruning Neural Networks at Initialization](https://mlsanity.com/paper/1906.06307/) (2019)
- [Fast ConvNets Using Group-wise Brain Damage](https://mlsanity.com/paper/1506.02515/) (2015)
- [Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error](https://mlsanity.com/paper/1808.08558/) (2018)

## Abstract (arXiv)

Capsule Networks (CapsNets) are a generation of image classifiers with proven advantages over Convolutional Neural Networks (CNNs). Better robustness to affine transformation and overlapping image detection are some of the benefits associated with CapsNets. However, CapsNets cannot be classified as resource-efficient deep learning architecture due to the high number of Primary Capsules (PCs). In addition, CapsNets' training and testing are slow and resource hungry. This paper investigates the possibility of Primary Capsules pruning in CapsNets on MNIST handwritten digits, Fashion-MNIST, CIFAR-10, and SVHN datasets. We show that a pruned version of CapsNet performs up to 9.90 times faster than the conventional architecture by removing 95 percent of Capsules without a loss of accuracy. Also, our pruned architecture saves on more than 95.36 percent of floating-point operations in the dynamic routing stage of the architecture. Moreover, we provide insight into why some datasets benefit significantly from pruning while others fall behind.