mlsanityData to 7 Oct 2026

Unsupervised part representation by Flow Capsules

arXiv 2011.13920 ↗First posted 27 Nov 2020cs.CV cs.LGcited by 25

Not on the map. Why?

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.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 9; 2023: 4; 2024: 1; 2025: 1.

25 papers.

Sort:

By area:

  1. 2021Conditional Object-Centric Learning from Videocited by 247
  2. 2021How to represent part-whole hierarchies in a neural networkcited by 123
  3. 2021Unsupervised Part Discovery from Contrastive Reconstructioncited by 57
  4. 2021Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objectscited by 50
  5. 2021The Emergence of Objectness: Learning Zero-Shot Segmentation from Videoscited by 45
  6. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programmingcited by 31
  7. 2023Towards Unsupervised Object Detection From LiDAR Point Cloudscited by 22
  8. 2023PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentationcited by 19
  9. 2022Unsupervised Segmentation in Real-World Images via Spelke Object Inferencecited by 15
  10. 2022Self-supervised Amodal Video Object Segmentationcited by 14
  11. 2021Unsupervised Co-part Segmentation through Assemblycited by 12
  12. 2022Learning with Capsules: A Surveycited by 10
13 more
  1. 2021Self-Supervised Monocular Scene Decomposition and Depth Estimationcited by 8
  2. 2021Towards Safe, Explainable, and Regulated Autonomous Drivingcited by 7
  3. 2022HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Networkcited by 7
  4. 2023Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumptioncited by 6
  5. 2023Graphics Capsule: Learning Hierarchical 3D Face Representations from 2D Imagescited by 3
  6. 2022Hybrid Gromov-Wasserstein Embedding for Capsule Learningcited by 1
  7. 2024EPOCH: Jointly Estimating the 3D Pose of Cameras and Humanscited by 1
  8. 2021Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Searchcited by 0
  9. 2021Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentationcited by 0
  10. 2022Unsupervised learning of features and object boundaries from local predictioncited by 0
  11. 2022APES: Articulated Part Extraction from Sprite Sheetscited by 0
  12. 2022Learning Latent Part-Whole Hierarchies for Point Cloudscited by 0
  13. 2025EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networkscited by 0