Bridging the Gap between Real-world and Synthetic Images for Testing
Autonomous Driving Systems
Bridging the Gap between Real-world and Synthetic Images for Testing
Autonomous Driving Systems
Deep Neural Networks (DNNs) for Autonomous Driving Systems (ADS) are typically trained on real-world images and tested using synthetic simulator images. This approach results in training and test datasets with dissimilar distributions, which can potentially lead to erroneously decreased test accuracy. To address this issue, the literature suggests applying domain-to-domain …