Hybrid Gromov-Wasserstein Embedding for Capsule Learning

TL;DR

This paper introduces a novel hybrid Gromov-Wasserstein framework for capsule learning that improves hierarchical modeling efficiency, enabling CapsNets to outperform deep CNNs in complex vision tasks while maintaining interpretability.

Contribution

We propose a new capsule learning method using a hybrid Gromov-Wasserstein approach with subcapsules, enhancing performance and efficiency over existing models.

Findings

Outperforms baseline capsule models in complex vision tasks

Enables application of capsules to object detection

Maintains interpretability and hierarchical structure

Abstract

Capsule networks (CapsNets) aim to parse images into a hierarchy of objects, parts, and their relations using a two-step process involving part-whole transformation and hierarchical component routing. However, this hierarchical relationship modeling is computationally expensive, which has limited the wider use of CapsNet despite its potential advantages. The current state of CapsNet models primarily focuses on comparing their performance with capsule baselines, falling short of achieving the same level of proficiency as deep CNN variants in intricate tasks. To address this limitation, we present an efficient approach for learning capsules that surpasses canonical baseline models and even demonstrates superior performance compared to high-performing convolution models. Our contribution can be outlined in two aspects: firstly, we introduce a group of subcapsules onto which an input vector is projected. Subsequently, we present the Hybrid Gromov-Wasserstein framework, which initially quantifies the dissimilarity between the input and the components modeled by the subcapsules, followed by determining their alignment degree through optimal transport. This innovative mechanism capitalizes on new insights into defining alignment between the input and subcapsules, based on the similarity of their respective component distributions. This approach enhances CapsNets' capacity to learn from intricate, high-dimensional data while retaining their interpretability and hierarchical structure. Our proposed model offers two distinct advantages: (i) its lightweight nature facilitates the application of capsules to more intricate vision tasks, including object detection; (ii) it outperforms baseline approaches in these demanding tasks.