2022/12/09 by Neslihan Köse, Neslihan Kose, Ranganath Krishnan +8 · 1 citation
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Autonomous Vehicle Technology and Safety #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Traffic Prediction and Management Techniques #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2212.04812
Accepted to ECCV 2022 workshop - Safe Artificial Intelligence for Automated Driving
arxiv created 2022/12/09 · openalex publication_date 2022/12/09 · arxiv updated 2022/12/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Reliable uncertainty quantification in deep neural networks is very crucial in safety-critical applications such as automated driving for trustworthy and informed decision-making. Assessing the quality of uncertainty estimates is challenging as ground truth for uncertainty estimates is not available. Ideally, in a well-calibrated model, uncertainty estimates should perfectly correlate with model error. We propose a novel error aligned uncertainty optimization method and introduce a trainable loss function to guide the models to yield good quality uncertainty estimates aligning with the model error. Our approach targets continuous structured prediction and regression tasks, and is evaluated on multiple datasets including a large-scale vehicle motion prediction task involving real-world distributional shifts. We demonstrate that our method improves average displacement error by 1.69% and 4.69%, and the uncertainty correlation with model error by 17.22% and 19.13% as quantified by Pearson correlation coefficient on two state-of-the-art baselines.