# Interpretable Graph Capsule Networks for Object Recognition

arXiv: https://arxiv.org/abs/2012.01674 · HTML: https://mlsanity.com/paper/2012.01674/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 12 of 12)

- [Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2204.07321/) (2022)
- [Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds](https://mlsanity.com/paper/2403.05247/) (2024)
- [Effective and Efficient Vote Attack on Capsule Networks](https://mlsanity.com/paper/2102.10055/) (2021)
- [Capsule Network is Not More Robust than Convolutional Network](https://mlsanity.com/paper/2103.15459/) (2021)
- [Learning with Capsules: A Survey](https://mlsanity.com/paper/2206.02664/) (2022)
- [Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption](https://mlsanity.com/paper/2301.01583/) (2023)
- [Semantic-aware Modular Capsule Routing for Visual Question Answering](https://mlsanity.com/paper/2207.10404/) (2022)
- [Capsule Networks Do Not Need to Model Everything](https://mlsanity.com/paper/2204.01298/) (2022)
- [CapsNet for Medical Image Segmentation](https://mlsanity.com/paper/2203.08948/) (2022)
- [Explainability and Robustness of Deep Visual Classification Models](https://mlsanity.com/paper/2301.01343/) (2023)
- [Towards the Characterization of Representations Learned via Capsule-based Network Architectures](https://mlsanity.com/paper/2305.05349/) (2023)
- [PR-CapsNet: Pseudo-Riemannian Capsule Network with Adaptive Curvature Routing for Graph Learning](https://mlsanity.com/paper/2512.08218/) (2025)

## Abstract (arXiv)

Capsule Networks, as alternatives to Convolutional Neural Networks, have been proposed to recognize objects from images. The current literature demonstrates many advantages of CapsNets over CNNs. However, how to create explanations for individual classifications of CapsNets has not been well explored. The widely used saliency methods are mainly proposed for explaining CNN-based classifications; they create saliency map explanations by combining activation values and the corresponding gradients, e.g., Grad-CAM. These saliency methods require a specific architecture of the underlying classifiers and cannot be trivially applied to CapsNets due to the iterative routing mechanism therein. To overcome the lack of interpretability, we can either propose new post-hoc interpretation methods for CapsNets or modifying the model to have build-in explanations. In this work, we explore the latter. Specifically, we propose interpretable Graph Capsule Networks (GraCapsNets), where we replace the routing part with a multi-head attention-based Graph Pooling approach. In the proposed model, individual classification explanations can be created effectively and efficiently. Our model also demonstrates some unexpected benefits, even though it replaces the fundamental part of CapsNets. Our GraCapsNets achieve better classification performance with fewer parameters and better adversarial robustness, when compared to CapsNets. Besides, GraCapsNets also keep other advantages of CapsNets, namely, disentangled representations and affine transformation robustness.