Novelty Detection and Analysis of Traffic Scenario Infrastructures in the Latent Space of a Vision Transformer-Based Triplet Autoencoder

TL;DR

This paper introduces a novel triplet autoencoder using vision transformers to detect unseen traffic scenario infrastructures by shaping the latent space with expert knowledge, outperforming existing outlier detection methods.

Contribution

The work presents a new triplet autoencoder architecture with vision transformers that effectively detects novel traffic scenarios by leveraging connectivity graph-based training.

Findings

Outperforms state-of-the-art outlier detection methods

Highlights importance of triplet autoencoder with vision transformers

Uses expert knowledge to shape the latent space

Abstract

Detecting unknown and untested scenarios is crucial for scenario-based testing. Scenario-based testing is considered to be a possible approach to validate autonomous vehicles. A traffic scenario consists of multiple components, with infrastructure being one of it. In this work, a method to detect novel traffic scenarios based on their infrastructure images is presented. An autoencoder triplet network provides latent representations for infrastructure images which are used for outlier detection. The triplet training of the network is based on the connectivity graphs of the infrastructure. By using the proposed architecture, expert-knowledge is used to shape the latent space such that it incorporates a pre-defined similarity in the neighborhood relationships of an autoencoder. An ablation study on the architecture is highlighting the importance of the triplet autoencoder combination. The best performing architecture is based on vision transformers, a convolution-free attention-based network. The presented method outperforms other state-of-the-art outlier detection approaches.