Inference and Learning for Generative Capsule Models

• URL: http://arxiv.org/abs/2209.03115v1
• Date: Wed, 7 Sep 2022 13:05:47 GMT
• Title: Inference and Learning for Generative Capsule Models
• Authors: Alfredo Nazabal, Nikolaos Tsagkas, Christopher K. I. Williams
• Abstract summary: Capsule networks aim to encode knowledge of and reason about the relationship between an object and its parts. We specify a generative model for such data, and derive a variational algorithm for inferring the transformation of each model object. We also study an alternative inference algorithm based on the RANSAC method of Fischler and Bolles (1981).
• Score: 5.1081420619330515
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 variational algorithm for inferring the transformation of each model object in a scene, and the assignments of observed parts to the objects. We derive a learning algorithm for the object models, based on variational expectation maximization (Jordan et al., 1999). We also study an alternative inference algorithm based on the RANSAC method of Fischler and Bolles (1981). We apply these inference methods 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).

Related papers

• Bayesian Beta-Bernoulli Process Sparse Coding with Deep Neural Networks [11.937283219047984]
  Several approximate inference methods have been proposed for deep discrete latent variable models. We propose a non-parametric iterative algorithm for learning discrete latent representations in such deep models. We evaluate our method across datasets with varying characteristics and compare our results to current amortized approximate inference methods.
  arXiv  Detail & Related papers  (2023-03-14T20:50:12Z)
• ModelDiff: A Framework for Comparing Learning Algorithms [86.19580801269036]
  We study the problem of (learning) algorithm comparison, where the goal is to find differences between models trained with two different learning algorithms. We present ModelDiff, a method that leverages the datamodels framework to compare learning algorithms based on how they use their training data.
  arXiv  Detail & Related papers  (2022-11-22T18:56:52Z)
• An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs [67.23285413610243]
  Self-supervision based on the information extracted from large knowledge graphs has been shown to improve the generalization of language models. We study the effect of knowledge sampling strategies and sizes that can be used to generate synthetic data for adapting language models.
  arXiv  Detail & Related papers  (2022-05-21T19:49:04Z)
• Prototypical Model with Novel Information-theoretic Loss Function for Generalized Zero Shot Learning [3.870962269034544]
  Generalized zero shot learning (GZSL) is still a technical challenge of deep learning. We address the quantification of the knowledge transfer and semantic relation from an information-theoretic viewpoint. We propose three information-theoretic loss functions for deterministic GZSL model.
  arXiv  Detail & Related papers  (2021-12-06T16:01:46Z)
• Inference for Generative Capsule Models [4.454557728745761]
  Capsule networks aim to encode knowledge and reason about the relationship between an object and its parts. Data is generated from multiple geometric objects at arbitrary translations, rotations and scales. We derive a variational algorithm for inferring the transformation of each object and the assignments of points to parts of the objects.
  arXiv  Detail & Related papers  (2021-03-11T14:10:29Z)
• Generalized Matrix Factorization: efficient algorithms for fitting generalized linear latent variable models to large data arrays [62.997667081978825]
  Generalized Linear Latent Variable models (GLLVMs) generalize such factor models to non-Gaussian responses. Current algorithms for estimating model parameters in GLLVMs require intensive computation and do not scale to large datasets. We propose a new approach for fitting GLLVMs to high-dimensional datasets, based on approximating the model using penalized quasi-likelihood.
  arXiv  Detail & Related papers  (2020-10-06T04:28:19Z)
• DecAug: Augmenting HOI Detection via Decomposition [54.65572599920679]
  Current algorithms suffer from insufficient training samples and category imbalance within datasets. We propose an efficient and effective data augmentation method called DecAug for HOI detection. Experiments show that our method brings up to 3.3 mAP and 1.6 mAP improvements on V-COCO and HICODET dataset.
  arXiv  Detail & Related papers  (2020-10-02T13:59:05Z)
• Model Fusion with Kullback--Leibler Divergence [58.20269014662046]
  We propose a method to fuse posterior distributions learned from heterogeneous datasets. Our algorithm relies on a mean field assumption for both the fused model and the individual dataset posteriors.
  arXiv  Detail & Related papers  (2020-07-13T03:27:45Z)
• Evaluating the Disentanglement of Deep Generative Models through Manifold Topology [66.06153115971732]
  We present a method for quantifying disentanglement that only uses the generative model. We empirically evaluate several state-of-the-art models across multiple datasets.
  arXiv  Detail & Related papers  (2020-06-05T20:54:11Z)
• Characterizing and Avoiding Problematic Global Optima of Variational Autoencoders [28.36260646471421]
  Variational Auto-encoders (VAEs) are deep generative latent variable models. Recent work shows that traditional training methods tend to yield solutions that violate desiderata. We show that both issues stem from the fact that the global optima of the VAE training objective often correspond to undesirable solutions.
  arXiv  Detail & Related papers  (2020-03-17T15:14:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.