The Multi-Entity Variational Autoencoder

By Charlie Nash, S. M. Ali Eslami, Christopher P. Burgess, Irina Higgins, Daniel Zoran, Theophane Weber, Peter W. Battaglia. 2018

Subfields: Generative Models, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

In Representation & Self-Supervised Learning

Citations in the corpus

Object-Centric Learning with Slot Attention (2020, background): “[38] Charlie Nash, SM Ali Eslami, Chris Burgess, Irina Higgins, Daniel Zoran, Theophane Weber, and Peter Battaglia.”
Reconciling deep learning with symbolic artificial intelligence: representing objects and relations (2019, background): “Given that the aim here is to encode the data in terms of objects and relations between objects, it is clear that this work needs to be extended to the multi-object setting, and some early progress along these lines has been made [36].”
On the Binding Problem in Artificial Neural Networks (2020, methodology): “Although they are not usually advertised as object representations in this way, several recent approaches, such as Relation Networks (Santoro et al., 2017), the Multi-Entity VAE (Nash et al., 2017), or the works by Zambaldi et al. (2019); Stanić et al. (2020) explicitly treat each spatial position i”
Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs (2019, methodology): “However, the CoordConv technique had been used beforehand [Zhao et al., 2015, Liang et al., 2015, Watters et al., 2017, Wojna et al., 2017, Perez et al., 2017, Nash et al., 2017, Ulyanov et al., 2017] and its origin is unclear.”
A Case for Object Compositionality in Deep Generative Models of Images (2018, methodology): “Following prior work, we consider different representational slots for each object (Greff et al., 2017; Nash et al., 2017), and a relational mechanism that preserves this separation accordingly (Zambaldi et al., 2018).”
D’ya Like DAGs? A Survey on Structure Learning and Causal Discovery (2021, methodology): “Examples of hybrid approaches include methods such as Recurrent Independent Mechanisms [76], graph networks [11, 12, 213], and a large body of work on scene understanding [116, 155, 171, 173, 270].”
Contrastive Learning of Structured World Models (2019, background): “…the problem of object discovery from visual data in a completely unsupervised or self-supervised manner (Eslami et al., 2016; Greff et al., 2017; Nash et al., 2017; van Steenkiste et al., 2018; Kosiorek et al., 2018; Jan-ner et al., 2019; Xu et al., 2019; Burgess et al., 2019; Greff et al.,…”