LE-CapsNet: A Light and Enhanced Capsule Network

Pouya Shiri, Amirali Baniasadi
11/12/2025
cs.CV

No confident code implementation found for this paper.

Abstract

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%).

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network

91% match2025

DL-CapsNet: A Deep and Light Capsule Network

91% match2025

Raw Instinct: Trust Your Classifiers and Skip the Conversion

85% match2024

KAN-Mixers: a new deep learning architecture for image classification

85% match2025

KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional Elements

84% match2 repos32024

ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification

83% match1 repo422026

Cite this paper

@article{shiri2025lecapsnet,
  title  = {LE-CapsNet: A Light and Enhanced Capsule Network},
  author = {Pouya Shiri and Amirali Baniasadi},
  year   = {2025},
  eprint = {2511.11708},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2511.11708v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2511.11708.svg)](https://codeofpaper.com/paper/2511.11708)

Discussion