Relationships from Entity Stream

by   Martin Andrews, et al.

Relational reasoning is a central component of intelligent behavior, but has proven difficult for neural networks to learn. The Relation Network (RN) module was recently proposed by DeepMind to solve such problems, and demonstrated state-of-the-art results on a number of datasets. However, the RN module scales quadratically in the size of the input, since it calculates relationship factors between every patch in the visual field, including those that do not correspond to entities. In this paper, we describe an architecture that enables relationships to be determined from a stream of entities obtained by an attention mechanism over the input field. The model is trained end-to-end, and demonstrates equivalent performance with greater interpretability while requiring only a fraction of the model parameters of the original RN module.


A simple neural network module for relational reasoning

Relational reasoning is a central component of generally intelligent beh...

Relational Gating for "What If" Reasoning

This paper addresses the challenge of learning to do procedural reasonin...

Visual-Relation Conscious Image Generation from Structured-Text

Generating realistic images from text descriptions is a challenging prob...

Modeling Relationships in Referential Expressions with Compositional Modular Networks

People often refer to entities in an image in terms of their relationshi...

Referring Relationships

Images are not simply sets of objects: each image represents a web of in...

Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph

Visual relationship reasoning is a crucial yet challenging task for unde...

Please sign up or login with your details

Forgot password? Click here to reset