# Towards the Characterization of Representations Learned via Capsule-based Network Architectures

arXiv: https://arxiv.org/abs/2305.05349 · HTML: https://mlsanity.com/paper/2305.05349/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 61 references that are in the map.
- First posted on arXiv 9 May 2023.

## Builds on (most cited first, 30 of 35)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [A Survey of Deep Learning Techniques for Autonomous Driving](https://mlsanity.com/paper/1910.07738/) (2019)
- [Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019](https://mlsanity.com/paper/1911.13288/) (2019)
- [Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts](https://mlsanity.com/paper/1406.2031/) (2014)
- [Interpretable Convolutional Neural Networks](https://mlsanity.com/paper/1710.00935/) (2017)
- [Generating Visual Explanations](https://mlsanity.com/paper/1603.08507/) (2016)
- [Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI](https://mlsanity.com/paper/2003.07258/) (2020)
- [Stacked Capsule Autoencoders](https://mlsanity.com/paper/1906.06818/) (2019)
- [Efficient-CapsNet: Capsule Network with Self-Attention Routing](https://mlsanity.com/paper/2101.12491/) (2021)
- [Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks](https://mlsanity.com/paper/1712.06302/) (2017)
- [Do semantic parts emerge in Convolutional Neural Networks?](https://mlsanity.com/paper/1607.03738/) (2016)
- [A Capsule Network for Recommendation and Explaining What You Like and Dislike](https://mlsanity.com/paper/1907.00687/) (2019)
- [Interpretable Graph Capsule Networks for Object Recognition](https://mlsanity.com/paper/2012.01674/) (2020)
- [Text Classification using Capsules](https://mlsanity.com/paper/1808.03976/) (2018)
- [CapsNet comparative performance evaluation for image classification](https://mlsanity.com/paper/1805.11195/) (2018)
- [A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks](https://mlsanity.com/paper/1606.07757/) (2016)
- [Dynamic Routing on Deep Neural Network for Thoracic Disease Classification and Sensitive Area Localization](https://mlsanity.com/paper/1808.05744/) (2018)
- [iCaps: An Interpretable Classifier via Disentangled Capsule Networks](https://mlsanity.com/paper/2008.08756/) (2020)
- [Improved Explainability of Capsule Networks: Relevance Path by Agreement](https://mlsanity.com/paper/1802.10204/) (2018)
- [Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption](https://mlsanity.com/paper/2301.01583/) (2023)
- [iCapsNets: Towards Interpretable Capsule Networks for Text Classification](https://mlsanity.com/paper/2006.00075/) (2020)

## Abstract (arXiv)

Capsule Networks (CapsNets) have been re-introduced as a more compact and interpretable alternative to standard deep neural networks. While recent efforts have proved their compression capabilities, to date, their interpretability properties have not been fully assessed. Here, we conduct a systematic and principled study towards assessing the interpretability of these types of networks. Moreover, we pay special attention towards analyzing the level to which part-whole relationships are indeed encoded within the learned representation. Our analysis in the MNIST, SVHN, PASCAL-part and CelebA datasets suggest that the representations encoded in CapsNets might not be as disentangled nor strictly related to parts-whole relationships as is commonly stated in the literature.