Estimating the uncertainty of a neural network plays a fundamental role in safety-critical settings. In perception for autonomous driving, measuring the uncertainty means providing additional calibrated information to downstream tasks, such as path planning, that can use it towards safe navigation. In this work, we propose a novel sampling-free uncertainty estimation method for object detection. We call it CertainNet, and it is the first to provide separate uncertainties for each output signal: objectness, class, location and size. To achieve this, we propose an uncertainty-aware heatmap, and exploit the neighboring bounding boxes provided by the detector at inference time. We evaluate the detection performance and the quality of the different uncertainty estimates separately, also with challenging out-of-domain samples: BDD100K and nuImages with models trained on KITTI. Additionally, we propose a new metric to evaluate location and size uncertainties. When transferring to unseen datasets, CertainNet generalizes substantially better than previous methods and an ensemble, while being real-time and providing high quality and comprehensive uncertainty estimates.
Sampling-based Task and Kinodynamic Motion Planning under Semantic Uncertainty
Kevin T. Crofton Department of Aerospace and Ocean Engineering, Virginia Tech（弗吉尼亚理工大学凯文·T·克罗夫顿航空航天与海洋工程系）；Smead Department of Aerospace Engineering Sciences, University of Colorado Boulder（科罗拉多大学博尔德分校斯米德航空航天工程科学系）
Uncertainty Propagation for Echocardiography Clinical Metric Estimation via Contour Sampling
University of Sherbrooke（谢布鲁克大学）；INSA（国立应用科学学院）；Universite Claude Bernard Lyon 1（里昂第一大学（克洛德·贝尔纳））；CNRS（法国国家科学研究中心）；Inserm（法国国家健康与医学研究院）；CREATIS（CREATIS研究机构）；Ultromics Ltd.（Ultromics有限公司）；King’s College London（伦敦国王学院）
Inherent Brain Segmentation Quality Control from Fully ConvNet Monte Carlo Sampling
LMU München（慕尼黑大学）；Technische Universität München（慕尼黑工业大学）；German Center for Neurodegenerative Diseases (DZNE)（德国神经退行性疾病中心）；Johns Hopkins University（约翰斯·霍普金斯大学）
Quantifying the Uncertainty in Model Parameters Using Gaussian Process-Based Markov Chain Monte Carlo: An Application to Cardiac Electrophysiological Models
Rochester Institute of Technology（罗切斯特理工学院）；Dalhousie University（达尔豪斯大学）
Active Learning in Brain Tumor Segmentation with Uncertainty Sampling, Annotation Redundancy Restriction, and Data Initialization
Warren Alpert Medical School of Brown University（布朗大学沃伦·阿尔珀特医学院）；Rhode Island Hospital（罗德岛医院）；Perelman School of Medicine at the University of Pennsylvania（宾夕法尼亚大学佩雷尔曼医学院）；Second Xiangya Hospital of Central South University（中南大学湘雅二医院）；University of Virginia（弗吉尼亚大学）；Johns Hopkins University（约翰霍普金斯大学）；Central South University（中南大学）；Brown University（布朗大学）
Uncertainty-aware Sampling for Long-tailed Semi-supervised Learning
East China Normal University（华东师范大学）；Kargobot of DiDi（滴滴出行Kargobot）；Shanghai Jiao Tong University（上海交通大学）；Tsinghua Berkeley Shenzhen Institute（清华大学深圳国际研究生院（清华-伯克利深圳学院））；Toronto Metropolitan University（多伦多都会大学）
Endo-NeRF++: Uncertainty-Aware Neural Rendering with Multi-Resolution Hash Encoding for Dynamic Surgical Scene Reconstruction
Finnish Center for Artificial Intelligence (FCAI)（芬兰人工智能中心）；ELLIS Unit Helsinki（欧洲学习与智能系统研究所赫尔辛基分部）；University of Helsinki（赫尔辛基大学）；Institute for Urban Studies (Urbaria)（城市研究所）；Institute of Sustainability Science (HELSUS)（可持续发展科学研究所）
