# LE-CapsNet: A Light and Enhanced Capsule Network

arXiv: https://arxiv.org/abs/2511.11708 · HTML: https://mlsanity.com/paper/2511.11708/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 8 references that are in the map.
- First posted on arXiv 12 Nov 2025.

## Builds on (most cited first, 5 of 5)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [DeepCaps: Going Deeper with Capsule Networks](https://mlsanity.com/paper/1904.09546/) (2019)
- [The Multi-Lane Capsule Network (MLCN)](https://mlsanity.com/paper/1902.08431/) (2019)
- [Quick-CapsNet (QCN): A fast alternative to Capsule Networks](https://mlsanity.com/paper/2510.07600/) (2025)

## Abstract (arXiv)

Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its different structure. In addition, CapsNet is resource-hungry, includes many parameters and lags in accuracy compared to CNNs. In this work, we propose LE-CapsNet as a light, enhanced and more accurate variant of CapsNet. Using 3.8M weights, LECapsNet obtains 76.73% accuracy on the CIFAR-10 dataset while performing inference 4x faster than CapsNet. In addition, our proposed network is more robust at detecting images with affine transformations compared to CapsNet. We achieve 94.3% accuracy on the AffNIST dataset (compared to CapsNet 90.52%).