# Traffic Scene Similarity: a Graph-based Contrastive Learning Approach

arXiv: https://arxiv.org/abs/2309.09720 · HTML: https://mlsanity.com/paper/2309.09720/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 18 Sep 2023.

## Builds on (most cited first, 8 of 8)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps](https://mlsanity.com/paper/1910.03088/) (2019)
- [A survey on trajectory clustering analysis](https://mlsanity.com/paper/1802.06971/) (2018)
- [Towards Traffic Scene Description: The Semantic Scene Graph](https://mlsanity.com/paper/2111.10196/) (2021)
- [Unsupervised and Supervised Learning with the Random Forest Algorithm for Traffic Scenario Clustering and Classification](https://mlsanity.com/paper/2004.02126/) (2020)
- [Deep Representation Learning and Clustering of Traffic Scenarios](https://mlsanity.com/paper/2007.07740/) (2020)
- [Expert-LaSTS: Expert-Knowledge Guided Latent Space for Traffic Scenarios](https://mlsanity.com/paper/2207.09120/) (2022)
- [Self Supervised Clustering of Traffic Scenes using Graph Representations](https://mlsanity.com/paper/2211.15508/) (2022)

## Built on by (most cited first, 5 of 5)

- [Spatial Retrieval Augmented Autonomous Driving](https://mlsanity.com/paper/2512.06865/) (2025)
- [Driving-RAG: Driving Scenarios Embedding, Search, and RAG Applications](https://mlsanity.com/paper/2504.04419/) (2025)
- [Structure-preserving contrastive learning for spatial time series](https://mlsanity.com/paper/2502.06380/) (2025)
- [Exploring Semantic Clustering and Similarity Search for Heterogeneous Traffic Scenario Graph](https://mlsanity.com/paper/2507.05086/) (2025)
- [Behavior-Centric Extraction of Scenarios from Highway Traffic Data and their Domain-Knowledge-Guided Clustering using CVQ-VAE](https://mlsanity.com/paper/2603.16964/) (2026)

## Abstract (arXiv)

Ensuring validation for highly automated driving poses significant obstacles to the widespread adoption of highly automated vehicles. Scenario-based testing offers a potential solution by reducing the homologation effort required for these systems. However, a crucial prerequisite, yet unresolved, is the definition and reduction of the test space to a finite number of scenarios. To tackle this challenge, we propose an extension to a contrastive learning approach utilizing graphs to construct a meaningful embedding space. Our approach demonstrates the continuous mapping of scenes using scene-specific features and the formation of thematically similar clusters based on the resulting embeddings. Based on the found clusters, similar scenes could be identified in the subsequent test process, which can lead to a reduction in redundant test runs.