Search papers, labs, and topics across Lattice.
This paper addresses the limitations of fixed confidence thresholds in multi-task autonomous driving systems by introducing a confidence threshold sensitivity analysis to optimize decision boundaries for different tasks. They demonstrate that adaptive threshold selection improves F1-scores compared to fixed thresholds. To facilitate research in this area, they also introduce IUST-XAI-AD, a new dataset with human annotations for driving decisions and reasoning, designed to address the gap in domain-specific evaluation benchmarks and capture cross-cultural driving behavior.
Fixed confidence thresholds are holding back explainable autonomous driving systems, but this new adaptive approach and dataset could unlock better performance and cross-cultural understanding.
Scene understanding is a vital part of autonomous driving systems, which requires the use of deep learning models. Deep learning methods are intrinsically black box models, which lack transparency and safety in autonomous driving. To make these systems transparent, multi-task visual understanding has become crucial for explainable autonomous driving perception systems, where simultaneous prediction of multiple driving behaviors and their underlying explanations is essential for safe navigation and human trust in autonomous vehicles. In order to design an accurate and cross-cultural explainable autonomous driving system, we introduce a comprehensive confidence threshold sensitivity analysis that evaluates various threshold values to identify optimal decision boundaries for different tasks. Our analysis demonstrates that traditional fixed threshold approaches are suboptimal for multi-task scenarios. Through extensive evaluation, we demonstrate that our adaptive threshold selection methodology improves F1-scores across different tasks. In addition, we introduce IUST-XAI-AD, a novel dataset consisting of 958 images with human annotations for driving decisions and corresponding reasoning. This dataset addresses the critical gap in domain-specific evaluation benchmarks for distinct driving contexts and provides a more challenging test environment compared to existing datasets. Experimental results demonstrate that confidence threshold sensitivity analysis can significantly improve model performance, while the introduction of the IUST-XAI-AD dataset reveals important insights about cross-cultural driving behavior patterns. The combined contributions of this work provide both methodological advances and practical evaluation tools that can accelerate the development of more reliable, explainable, and culturally-adaptive autonomous driving systems for global deployment.
