Deep Neural Networks and Data for Automated Driving

Chapter 1 Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety

Chapter 2 Does Redundancy in AI Perception Systems Help to Test for Super-Human Automated Driving Performance?

Chapter 3 Analysis and Comparison of Datasets by Leveraging Data Distributions in Latent Spaces

Chapter 4 Optimized Data Synthesis for DNN Training and Validation by Sensor Artifact Simulation

Chapter 5 Improved DNN Robustness by Multi-task Training with an Auxiliary Self-Supervised Task

Chapter 6 Improving Transferability of Generated Universal Adversarial Perturbations for Image Classification and Segmentation

Chapter 7 Invertible Neural Networks for Understanding Semantics of Invariances of CNN Representations

Chapter 8 Confidence Calibration for Object Detection and Segmentation

Chapter 9 Uncertainty Quantification for Object Detection: Output- and Gradient-Based Approaches

Chapter 11 Evaluating Mixture-of-Experts Architectures for Network Aggregation

Chapter 12 Safety Assurance of Machine Learning for Perception Functions

Chapter 13 A Variational Deep Synthesis Approach for Perception Validation

Chapter 14 The Good and the Bad: Using Neuron Coverage as a DNN Validation Technique

Chapter 15 Joint Optimization for DNN Model Compression and Corruption Robustness