Synthetic Similarity Search in Automotive Production

TL;DR

This paper introduces a novel automotive visual inspection method that uses synthetic data and a foundation model for similarity search, reducing the need for large annotated datasets while maintaining high accuracy.

Contribution

It presents a new image classification pipeline combining foundation model-based similarity search with synthetic data, enabling effective automotive inspection without extensive real data.

Findings

Achieves high classification accuracy with synthetic data

Effective in eight real-world inspection scenarios

Reduces reliance on costly annotated datasets

Abstract

Visual quality inspection in automotive production is essential for ensuring the safety and reliability of vehicles. Computer vision (CV) has become a popular solution for these inspections due to its cost-effectiveness and reliability. However, CV models require large, annotated datasets, which are costly and time-consuming to collect. To reduce the need for extensive training data, we propose a novel image classification pipeline that combines similarity search using a vision-based foundation model with synthetic data. Our approach leverages a DINOv2 model to transform input images into feature vectors, which are then compared to pre-classified reference images using cosine distance measurements. By utilizing synthetic data instead of real images as references, our pipeline achieves high classification accuracy without relying on real data. We evaluate this approach in eight real-world inspection scenarios and demonstrate that it meets the high performance requirements of production environments.