# Stacked Capsule Autoencoders

arXiv: https://arxiv.org/abs/1906.06818 · HTML: https://mlsanity.com/paper/1906.06818/

## Key facts

- Cited by 82 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2019.

## Built on by (most cited first, 30 of 82)

- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [How to represent part-whole hierarchies in a neural network](https://mlsanity.com/paper/2102.12627/) (2021)
- [Generative Adversarial Transformers](https://mlsanity.com/paper/2103.01209/) (2021)
- [GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement](https://mlsanity.com/paper/2104.09958/) (2021)
- [SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning](https://mlsanity.com/paper/2110.04361/) (2021)
- [Unsupervised Part Discovery from Contrastive Reconstruction](https://mlsanity.com/paper/2111.06349/) (2021)
- [Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames](https://mlsanity.com/paper/2302.04973/) (2023)
- [Unsupervised Layered Image Decomposition into Object Prototypes](https://mlsanity.com/paper/2104.14575/) (2021)
- [Unsupervised Learning of Group Invariant and Equivariant Representations](https://mlsanity.com/paper/2202.07559/) (2022)
- [GraphFPN: Graph Feature Pyramid Network for Object Detection](https://mlsanity.com/paper/2108.00580/) (2021)
- [DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders](https://mlsanity.com/paper/2108.08557/) (2021)
- [Learning Layer-wise Equivariances Automatically using Gradients](https://mlsanity.com/paper/2310.06131/) (2023)
- [Towards Unsupervised Object Detection From LiDAR Point Clouds](https://mlsanity.com/paper/2311.02007/) (2023)
- [Visual Parser: Representing Part-whole Hierarchies with Transformers](https://mlsanity.com/paper/2107.05790/) (2021)
- [Capturing the objects of vision with neural networks](https://mlsanity.com/paper/2109.03351/) (2021)
- [Unsupervised Motion Representation Learning with Capsule Autoencoders](https://mlsanity.com/paper/2110.00529/) (2021)
- [Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control](https://mlsanity.com/paper/2210.01969/) (2022)
- [Group Equivariant Subsampling](https://mlsanity.com/paper/2106.05886/) (2021)
- [Multi-task Hierarchical Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/2305.12633/) (2023)
- [Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision](https://mlsanity.com/paper/2404.15672/) (2024)
- [Capsule Network is Not More Robust than Convolutional Network](https://mlsanity.com/paper/2103.15459/) (2021)
- [Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention](https://mlsanity.com/paper/2304.03282/) (2023)
- [Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks](https://mlsanity.com/paper/2203.03282/) (2022)
- [Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence](https://mlsanity.com/paper/2103.00752/) (2021)
- [Learning with Capsules: A Survey](https://mlsanity.com/paper/2206.02664/) (2022)
- [Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planning](https://mlsanity.com/paper/2210.13461/) (2022)
- [Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?](https://mlsanity.com/paper/2305.17023/) (2023)
- [Test-time Adaptation with Slot-Centric Models](https://mlsanity.com/paper/2203.11194/) (2022)
- [State estimation with limited sensors -- A deep learning based approach](https://mlsanity.com/paper/2101.11513/) (2021)
- [HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network](https://mlsanity.com/paper/2203.10699/) (2022)

## Abstract (arXiv)

Objects are composed of a set of geometrically organized parts. We introduce an unsupervised capsule autoencoder (SCAE), which explicitly uses geometric relationships between parts to reason about objects. Since these relationships do not depend on the viewpoint, our model is robust to viewpoint changes. SCAE consists of two stages. In the first stage, the model predicts presences and poses of part templates directly from the image and tries to reconstruct the image by appropriately arranging the templates. In the second stage, SCAE predicts parameters of a few object capsules, which are then used to reconstruct part poses. Inference in this model is amortized and performed by off-the-shelf neural encoders, unlike in previous capsule networks. We find that object capsule presences are highly informative of the object class, which leads to state-of-the-art results for unsupervised classification on SVHN (55%) and MNIST (98.7%). The code is available at https://github.com/google-research/google-research/tree/master/stacked_capsule_autoencoders