# Unsupervised part representation by Flow Capsules

arXiv: https://arxiv.org/abs/2011.13920 · HTML: https://mlsanity.com/paper/2011.13920/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 25 of 25)

- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [How to represent part-whole hierarchies in a neural network](https://mlsanity.com/paper/2102.12627/) (2021)
- [Unsupervised Part Discovery from Contrastive Reconstruction](https://mlsanity.com/paper/2111.06349/) (2021)
- [Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects](https://mlsanity.com/paper/2112.11347/) (2021)
- [The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos](https://mlsanity.com/paper/2111.06394/) (2021)
- [VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming](https://mlsanity.com/paper/2202.04178/) (2022)
- [Towards Unsupervised Object Detection From LiDAR Point Clouds](https://mlsanity.com/paper/2311.02007/) (2023)
- [PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation](https://mlsanity.com/paper/2301.00954/) (2023)
- [Unsupervised Segmentation in Real-World Images via Spelke Object Inference](https://mlsanity.com/paper/2205.08515/) (2022)
- [Self-supervised Amodal Video Object Segmentation](https://mlsanity.com/paper/2210.12733/) (2022)
- [Unsupervised Co-part Segmentation through Assembly](https://mlsanity.com/paper/2106.05897/) (2021)
- [Learning with Capsules: A Survey](https://mlsanity.com/paper/2206.02664/) (2022)
- [Self-Supervised Monocular Scene Decomposition and Depth Estimation](https://mlsanity.com/paper/2110.11275/) (2021)
- [Towards Safe, Explainable, and Regulated Autonomous Driving](https://mlsanity.com/paper/2111.10518/) (2021)
- [HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network](https://mlsanity.com/paper/2203.10699/) (2022)
- [Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption](https://mlsanity.com/paper/2301.01583/) (2023)
- [Graphics Capsule: Learning Hierarchical 3D Face Representations from 2D Images](https://mlsanity.com/paper/2303.10896/) (2023)
- [Hybrid Gromov-Wasserstein Embedding for Capsule Learning](https://mlsanity.com/paper/2209.00232/) (2022)
- [EPOCH: Jointly Estimating the 3D Pose of Cameras and Humans](https://mlsanity.com/paper/2406.19726/) (2024)
- [Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search](https://mlsanity.com/paper/2104.00698/) (2021)
- [Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation](https://mlsanity.com/paper/2106.03330/) (2021)
- [Unsupervised learning of features and object boundaries from local prediction](https://mlsanity.com/paper/2205.14195/) (2022)
- [APES: Articulated Part Extraction from Sprite Sheets](https://mlsanity.com/paper/2206.02015/) (2022)
- [Learning Latent Part-Whole Hierarchies for Point Clouds](https://mlsanity.com/paper/2211.07082/) (2022)
- [EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networks](https://mlsanity.com/paper/2506.09895/) (2025)

## Abstract (arXiv)

Capsule networks aim to parse images into a hierarchy of objects, parts and relations. While promising, they remain limited by an inability to learn effective low level part descriptions. To address this issue we propose a way to learn primary capsule encoders that detect atomic parts from a single image. During training we exploit motion as a powerful perceptual cue for part definition, with an expressive decoder for part generation within a layered image model with occlusion. Experiments demonstrate robust part discovery in the presence of multiple objects, cluttered backgrounds, and occlusion. The part decoder infers the underlying shape masks, effectively filling in occluded regions of the detected shapes. We evaluate FlowCapsules on unsupervised part segmentation and unsupervised image classification.