3D object detection is an essential task for computer vision applications in autonomous vehicles and robotics. However, models often struggle to quantify detection reliability, leading to poor performance on unfamiliar scenes. We introduce a framework for quantifying uncertainty in 3D object detection by leveraging an evidential learning loss on Bird's Eye View representations in the 3D detector. These uncertainty estimates require minimal computational overhead and are generalizable across different architectures. We demonstrate both the efficacy and importance of these uncertainty estimates on identifying out-of-distribution scenes, poorly localized objects, and missing (false negative) detections; our framework consistently improves over baselines by 10-20% on average. Finally, we integrate this suite of tasks into a system where a 3D object detector auto-labels driving scenes and our uncertainty estimates verify label correctness before the labels are used to train a second model. Here, our uncertainty-driven verification results in a 1% improvement in mAP and a 1-2% improvement in NDS.
FedEU: Evidential Uncertainty-Driven Federated Fine-Tuning of Vision Foundation Models for Remote Sensing Image Segmentation
School of Artificial Intelligence, Wuhan University(武汉大学人工智能学院);School of Information Science and Engineering, Wuhan University of Science and Technology(武汉科技大学信息科学与工程学院);School of Computer Science, Wuhan University(武汉大学计算机学院)
EvCenterNet: Uncertainty Estimation for Object Detection using Evidential Learning
Fraunhofer IKS(弗劳恩霍夫智能认知系统研究所);University of Freiburg(弗赖堡大学);Federal University of Rio Grande(里奥格兰德联邦大学);University of Tech. Nuremberg(纽伦堡工业大学);TU München(慕尼黑工业大学)
Uncertainty-aware Evidential Fusion-based Learning for Semi-supervised Medical Image Segmentation
Key Laboratory of High Confidence Software Technologies (Peking University)(高可信软件技术重点实验室(北京大学));Department of Computer and Information Science, University of Macau(澳门大学计算机与信息科学系)
Uncertainty-Supervised Interpretable and Robust Evidential Segmentation
School of Data Science, Fudan University, Shanghai, China(复旦大学数据科学学院);Institute of Science and Technology for Brain-inspired intelligence, Fudan University, Shanghai, China(复旦大学脑启发式智能技术研究所);Nuffield Department of Population Health, University of Oxford, Oxford, UK(牛津大学人口健康牛津部门)
EPL: Evidential Prototype Learning for Semi-supervised Medical Image Segmentation
Key Laboratory of High Confidence Software Technologies (Peking University)(高可信软件技术重点实验室(北京大学));School of Computer Science, Peking University(北京大学计算机学院)
Medical Image Segmentation with Belief Function Theory and Deep Learning
University of Technology of Compiègne(贡比涅技术大学);Heudiasyc Laboratory(欧洲计算机科学与自动化研究院);University of Paris-Saclay(巴黎萨克雷大学);University of Artois(阿图瓦大学);ENSMM School(国立高等机械与微技术学院);University of Rouen(鲁昂大学)
Uncertainty-Error correlations in Evidential Deep Learning models for biomedical segmentation
Gryphon Center for Artificial Intelligence and Theoretical Sciences, Singapore University of Pennsylvania, Perelman School of Medicine, Department of Radiation Oncology(格雷芬人工智能与理论科学中心,新加坡大学匹兹堡大学,佩尔曼医学学院,放射肿瘤学系);Georgia Institute of Technology(佐治亚理工学院);University of Pennsylvania, Perelman School of Medicine, Department of Radiation Oncology(宾夕法尼亚大学,佩尔曼医学学院,放射肿瘤学系)
Mutual Evidential Deep Learning for Medical Image Segmentation
Key Laboratory of High Confidence Software Technologies (MOE) School of Computer Science Peking University(高可信软件技术重点实验室(MOE)计算机科学学院,北京大学);College of Computer and Information Science School of Software Southwest University(计算机与信息科学学院 软件学院 西南大学);Department of Computer and Information Science University of Macau(计算机与信息科学系 澳门大学)
Towards Reliable Medical Image Segmentation by Modeling Evidential Calibrated Uncertainty
National Key Laboratory of Fundamental Science on Synthetic Vision, the College of Computer Science, Sichuan University(国家基础科学合成视觉重点实验室、计算机科学学院、四川大学);Department of Radiology, West China Hospital, Sichuan University(放射科、西昌医院、四川大学);Saw Swee Hock School of Public Health, National University of Singapore(Saw Swee Hock 公共卫生学院、新加坡国立大学);Department of Mathematics, Sichuan University(数学系、四川大学);Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)(高性能计算研究所(IHPC)、科学、技术与研究局(A*STAR));Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore(创新与精准眼健康中心、 Yong Loo Lin 医学院、新加坡国立大学);Singapore Eye Research Institute, Singapore National Eye Centre(新加坡眼研究所、新加坡国家眼科中心)
Evidential Perfusion Physics-Informed Neural Networks with Residual Uncertainty Quantification
Cancer Biology, Seoul National University College of Medicine, Seoul, Korea(首尔国立大学医学院癌症生物学系);Radiology, Seoul National University Hospital, Seoul, Korea(首尔国立大学医院放射学);Bioengineering, Seoul National University, Seoul, Korea(首尔国立大学生物工程系);Biomedical Sciences, Seoul National University, Seoul, Korea(首尔国立大学生物医学科学);Radiology, Seoul National University College of Medicine, Seoul, Korea(首尔国立大学医学院放射学);Healthcare AI Research Institute, Seoul National University Hospital, Seoul, Korea(首尔国立大学医院健康人工智能研究院)
TMF-RSE: Tri-Modal Fusion with Regional Semantics and Evidential Uncertainty for Lung Severity Scoring
Institute of Applied Sciences and Intelligent Systems (ISASI), CNR(应用科学与智能系统研究所(ISASI),CNR);Department of Computer Science and Artificial Intelligence, University of the Basque Country (UPV/EHU)(巴斯克国家大学计算机科学与人工智能系);University of Salento(萨莱nton大学)
Deep, spatially coherent Inverse Sensor Models with Uncertainty Incorporation using the evidential Framework
Ford Werke GmbH(福特汽车公司(Ford Werke GmbH));Institute for Automotive Engineering, RWTH Aachen University(亚琛工业大学汽车工程研究所(Institute for Automotive Engineering, RWTH Aachen University))
Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty
The University of Texas at Dallas(德克萨斯大学达拉斯分校);US Army Research Laboratory(美国陆军研究实验室);University of Oslo(奥斯陆大学);Virginia Tech(弗吉尼亚理工大学);University of the District of Columbia(哥伦比亚特区大学)
DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Prediction
National University of Singapore;National University of Singapore Guangzhou Research Translation;Innovation Institute;Imperial College London;Peking Union Medical College Hospital, Chinese Academy of Medical Sciences \& Peking Union Medical College;Hunan University;Institute of High Performance Computing, Agency for Science, Technology;Research (A STAR)