# Capsule Network Performance on Complex Data

arXiv: https://arxiv.org/abs/1712.03480 · HTML: https://mlsanity.com/paper/1712.03480/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2017.

## Built on by (most cited first, 22 of 22)

- [Efficient-CapsNet: Capsule Network with Self-Attention Routing](https://mlsanity.com/paper/2101.12491/) (2021)
- [Recent advances for quantum classifiers](https://mlsanity.com/paper/2108.13421/) (2021)
- [Quantum Neural Network Classifiers: A Tutorial](https://mlsanity.com/paper/2206.02806/) (2022)
- [Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention](https://mlsanity.com/paper/2304.03282/) (2023)
- [Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption](https://mlsanity.com/paper/2301.01583/) (2023)
- [Graph Routing between Capsules](https://mlsanity.com/paper/2106.11531/) (2021)
- [XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks](https://mlsanity.com/paper/2111.10854/) (2021)
- [Training Deep Capsule Networks with Residual Connections](https://mlsanity.com/paper/2104.07393/) (2021)
- [Novel Dual-Channel Long Short-Term Memory Compressed Capsule Networks for Emotion Recognition](https://mlsanity.com/paper/2112.13350/) (2021)
- [Inferring Inference](https://mlsanity.com/paper/2310.03186/) (2023)
- [Momentum Capsule Networks](https://mlsanity.com/paper/2201.11091/) (2022)
- [A Novel Capsule Neural Network Based Model for Drowsiness Detection Using Electroencephalography Signals](https://mlsanity.com/paper/2204.01666/) (2022)
- [Capsule Network based Contrastive Learning of Unsupervised Visual Representations](https://mlsanity.com/paper/2209.11276/) (2022)
- [Effectiveness of the Recent Advances in Capsule Networks](https://mlsanity.com/paper/2210.05834/) (2022)
- [A Hybrid Transfer Learning Assisted Decision Support System for Accurate Prediction of Alzheimer Disease](https://mlsanity.com/paper/2310.08888/) (2023)
- [Leveraging Spatial and Semantic Feature Extraction for Skin Cancer Diagnosis with Capsule Networks and Graph Neural Networks](https://mlsanity.com/paper/2403.12009/) (2024)
- [Deep multi-prototype capsule networks](https://mlsanity.com/paper/2404.15445/) (2024)
- [The Convergence of Dynamic Routing between Capsules](https://mlsanity.com/paper/2501.06240/) (2025)
- [Capsule-ConvKAN: A Hybrid Neural Approach to Medical Image Classification](https://mlsanity.com/paper/2507.06417/) (2025)
- [DL-CapsNet: A Deep and Light Capsule Network](https://mlsanity.com/paper/2512.00061/) (2025)
- [One-Shot Identification with Different Neural Network Approaches](https://mlsanity.com/paper/2601.08278/) (2026)
- [Multiple Additive Neural Networks for Structured and Unstructured Data](https://mlsanity.com/paper/2604.26888/) (2026)

## Abstract (arXiv)

In recent years, convolutional neural networks (CNN) have played an important role in the field of deep learning. Variants of CNN's have proven to be very successful in classification tasks across different domains. However, there are two big drawbacks to CNN's: their failure to take into account of important spatial hierarchies between features, and their lack of rotational invariance. As long as certain key features of an object are present in the test data, CNN's classify the test data as the object, disregarding features' relative spatial orientation to each other. This causes false positives. The lack of rotational invariance in CNN's would cause the network to incorrectly assign the object another label, causing false negatives. To address this concern, Hinton et al. propose a novel type of neural network using the concept of capsules in a recent paper. With the use of dynamic routing and reconstruction regularization, the capsule network model would be both rotation invariant and spatially aware. The capsule network has shown its potential by achieving a state-of-the-art result of 0.25% test error on MNIST without data augmentation such as rotation and scaling, better than the previous baseline of 0.39%. To further test out the application of capsule networks on data with higher dimensionality, we attempt to find the best set of configurations that yield the optimal test error on CIFAR10 dataset.