SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks

TL;DR

SCENE introduces a heterogeneous graph neural network framework for reasoning about traffic scenes, effectively encoding diverse information and outperforming task-specific methods in node classification tasks.

Contribution

The paper presents a novel heterogeneous graph neural network approach for traffic scene understanding, demonstrating its effectiveness and transferability across domains.

Findings

Outperforms task-specific baselines in traffic scene node classification

Successfully transfers to knowledge graph node classification

Utilizes cascaded graph convolution layers for comprehensive encoding

Abstract

Understanding traffic scenes requires considering heterogeneous information about dynamic agents and the static infrastructure. In this work we propose SCENE, a methodology to encode diverse traffic scenes in heterogeneous graphs and to reason about these graphs using a heterogeneous Graph Neural Network encoder and task-specific decoders. The heterogeneous graphs, whose structures are defined by an ontology, consist of different nodes with type-specific node features and different relations with type-specific edge features. In order to exploit all the information given by these graphs, we propose to use cascaded layers of graph convolution. The result is an encoding of the scene. Task-specific decoders can be applied to predict desired attributes of the scene. Extensive evaluation on two diverse binary node classification tasks show the main strength of this methodology: despite being generic, it even manages to outperform task-specific baselines. The further application of our methodology to the task of node classification in various knowledge graphs shows its transferability to other domains.