paper-with-me

Papers

Inference for Generative Capsule Models

2021-03-11 · Alfredo Nazabal, Nikolaos Tsagkas, Christopher K. I. Williams

Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge and reason about the relationship between an object and its parts. In this paper we specify a \emph{generative} model for such data, and derive a variational algorithm for inferring the transformation of each object and the assignments of observed parts to the objects. We apply this model to (i) data generated from multiple geometric objects like squares and triangles ("constellations"), and (ii) data from a parts-based model of faces. Recent work by Kosiorek et al. [2019] has used amortized inference via stacked capsule autoencoders (SCAEs) to tackle this problem -- our results show that we significantly outperform them where we can make comparisons (on the constellations data).

📄 PDF Abstract BibTeX arXiv:2103.06676

Code (2)

anazabal/GenerativeCapsules 공식 구현
tsagkas/capsules 공식 구현

Tasks

Object

Similar Papers 제목 키워드 기반

Capsule Networks -- A Probabilistic Perspective

2020-04-07 · Lewis Smith, Lisa Schut, Yarin Gal, Mark van der Wilk

'Capsule' models try to explicitly represent the poses of objects, enforcing a linear relationship between an object's pose and that of its constituent parts. This modelling assumption should lead to robustness to viewpo…

Object

Capsule Networks as Generative Models

2022-09-06 · Alex B. Kiefer, Beren Millidge, Alexander Tschantz, Christopher L. Buckley

Capsule networks are a neural network architecture specialized for visual scene recognition. Features and pose information are extracted from a scene and then dynamically routed through a hierarchy of vector-valued nodes…

Scene Recognition

Inference and Learning for Generative Capsule Models

2022-09-07 · Alfredo Nazabal, Nikolaos Tsagkas, Christopher K. I. Williams

Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge of and reason about the relationship between an object and its parts. In this paper we specify a generative model for such data, and derive a variat…

Object

CapsuleGAN: Generative Adversarial Capsule Network

2018-02-17 · Ayush Jaiswal, Wael Abd-Almageed, Yue Wu, Premkumar Natarajan

We present Generative Adversarial Capsule Network (CapsuleGAN), a framework that uses capsule networks (CapsNets) instead of the standard convolutional neural networks (CNNs) as discriminators within the generative adver…

General ClassificationGenerative Adversarial Networkimage-classificationImage Classification+1

Learning with Capsules: A Survey

2022-06-06 · Fabio De Sousa Ribeiro, Kevin Duarte, Miles Everett, Georgios Leontidis 외

Capsule networks were proposed as an alternative approach to Convolutional Neural Networks (CNNs) for learning object-centric representations, which can be leveraged for improved generalization and sample complexity. Unl…

Graph Representation LearningRepresentation LearningSurvey