针对视觉语言 AI 的不确定性感知，本文区分认知与偶然不确定性，构建含 17.8 万 VQA 对比样本的 CertainlyUncertain 基准，并提出置信度加权准确率指标。
摘要：
承认其知识和推理中不可避免的不确定性，是 AI 系统真正真实可靠的先决条件。本文提出一种专属于视觉语言 AI 系统的不确定性分类体系，区分认知不确定性（源于信息缺失）与偶然不确定性（源于内在不可预测性），并进一步探究其中更细的类别。基于该分类体系，我们构建了基准数据集 CertainlyUncertain，包含 17.8 万个以对比对形式呈现的视觉问答（VQA）样本。其构建通过两种方式实现：1）对图像进行修复，使原本可回答的问题变为不可回答；2）利用图像描述提示大语言模型，生成可回答与不可回答的问题。此外，我们提出新指标置信度加权准确率，该指标与准确率和校准误差均具有良好相关性，以弥补现有指标的不足。
英文摘要：
The ability to acknowledge the inevitable uncertainty in their knowledge and reasoning is a prerequisite for AI systems to be truly truthful and reliable. In this paper, we present a taxonomy of uncertainty specific to vision-language AI systems, distinguishing between epistemic uncertainty (arising from a lack of information) and aleatoric uncertainty (due to inherent unpredictability), and further explore finer categories within. Based on this taxonomy, we synthesize a benchmark dataset, CertainlyUncertain, featuring 178K visual question answering (VQA) samples as contrastive pairs. This is achieved by 1) inpainting images to make previously answerable questions into unanswerable ones; and 2) using image captions to prompt large language models for both answerable and unanswerable questions. Additionally, we introduce a new metric confidence-weighted accuracy, that is well correlated with both accuracy and calibration error, to address the shortcomings of existing metrics.
UC Berkeley（加州大学伯克利分校）；Technical University of Munich（慕尼黑工业大学）
Human trajectory forecasting is an inherently multi-modal problem. Uncertainty in future trajectories stems from two sources: (a) sources that are known to the agent but unknown to the model, such as long term goals and (b)sources that are unknown to both the agent & the model, such as intent of other agents & irreducible randomness indecisions. We propose to factorize this uncertainty into its epistemic & aleatoric sources. We model the epistemic un-certainty through multimodality in long term goals and the aleatoric uncertainty through multimodality in waypoints& paths. To exemplify this dic…
University of Colorado Boulder（科罗拉多大学博尔德分校）；The Charles Stark Draper Laboratory, Inc.（查尔斯·斯塔克·德雷珀实验室公司）
Giving autonomous agents the ability to forecast their own outcomes and uncertainty will allow them to communicate their competencies and be used more safely. We accomplish this by using a learned world model of the agent system to forecast full agent trajectories over long time horizons. Real world systems involve significant sources of both aleatoric and epistemic uncertainty that compound and interact over time in the trajectory forecasts. We develop a deep generative world model that quantifies aleatoric uncertainty while incorporating the effects of epistemic uncertainty during the learni…
HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Model
Department of Earth, Environment, and Planetary Sciences, Brown University（布朗大学地球、环境与行星科学系）；Data Science Institute, Brown University（布朗大学数据科学研究院）；Department of Computer Science, Brown University（布朗大学计算机科学系）
Soil moisture is an important variable that determines floods, vegetation health, agriculture productivity, and land surface feedbacks to the atmosphere, etc. Accurately modeling soil moisture has important implications in both weather and climate models. The recently available satellite-based observations give us a unique opportunity to build data-driven models to predict soil moisture instead of using land surface models, but previously there was no uncertainty estimate. We tested Monte Carlo dropout (MCD) with an aleatoric term for our long short-term memory models for this problem, and ask…
Disentangling Aleatoric and Epistemic Uncertainty in Physics-Informed Neural Networks. Application to Insulation Material Degradation Prognostics
Department of Electronics and Computer Science（电子与计算机科学系）；Mondragon University（蒙得龙大学）；Research & Development（研发）；CARTIF Technology Centre（CARTIF技术中心）；Department of Physical Chemistry（物理化学系）；University of the Basque Country (EHU)（巴斯克国家大学（EHU））；Basque Centre for Applied Mathematics (BCAM)（巴斯克应用数学中心（BCAM））；Department of Computer Science and Artificial Intelligence（计算机科学与人工智能系）
CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model
Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore（南洋理工大学李科钦医学院，新加坡）；College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算与数据科学学院，新加坡）；Centre for Medical Technologies & Innovations, National Health Group, Singapore（国家健康集团医学技术与创新中心，新加坡）
Radboud University（拉德堡德大学）；University of Oxford（牛津大学）
Capturing uncertainty in models of complex dynamical systems is crucial to designing safe controllers. Stochastic noise causes aleatoric uncertainty, whereas imprecise knowledge of model parameters leads to epistemic uncertainty. Several approaches use formal abstractions to synthesize policies that satisfy temporal specifications related to safety and reachability. However, the underlying models exclusively capture aleatoric but not epistemic uncertainty, and thus require that model parameters are known precisely. Our contribution to overcoming this restriction is a novel abstraction-based co…
Interpretable Uncertainty Routing Separating Emotion Ambiguity from Distribution Shift in Facial Expression Recognition
Faculty of Business and Commerce, Kansai University（关西大学商学部）；Data Science and AI Innovation Research Promotion Center, Shiga University（滋贺大学数据科学与人工智能创新研究促进中心）；Graduate School of Data Science, Shiga University（滋贺大学数据科学研究科）
From Aleatoric to Epistemic: Exploring Uncertainty Quantification Techniques in Artificial Intelligence
University of Liverpool（利物浦大学）；University of Edinburgh（爱丁堡大学）；The University of Texas at Dallas（德州大学达拉斯分校）；Georgia Institute of Technology（佐治亚理工学院）；Emory University（埃默里大学）；Simon Fraser University（西蒙菲莎大学）；Kyoto University（京都大学）；Zhejiang University（浙江大学）；National Taiwan Normal University（国立台湾师范大学）；Indiana University（印第安纳大学）；Purdue University（普渡大学）；AppCubic（AppCubic公司）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；The Hong Kong University of Science and Technology（香港科技大学）
UbiQTree: Uncertainty Quantification in XAI with Tree Ensembles
Center for Artificial Intelligence in Public Health Research (ZKI-PH), Robert Koch Institute（人工智能在公共卫生研究中的中心（ZKI-PH），罗伯特· Koch 研究所）；Department of Mathematics and Computer Science, Freie Universität Berlin（数学与计算机科学系，柏林自由大学）
This position paper reflects on the state-of-the-art in decision-making under uncertainty. A classical assumption is that probabilities can sufficiently capture all uncertainty in a system. In this paper, the focus is on the uncertainty that goes beyond this classical interpretation, particularly by employing a clear distinction between aleatoric and epistemic uncertainty. The paper features an overview of Markov decision processes (MDPs) and extensions to account for partial observability and adversarial behavior. These models sufficiently capture aleatoric uncertainty but fail to account for…
Instituto de Ingenieria de Aragon (I3A)（阿拉贡工程研究所）；Universidad de Zaragoza（萨拉戈萨大学）
Affordances are a fundamental concept in robotics since they relate available actions for an agent depending on its sensory-motor capabilities and the environment. We present a novel Bayesian deep network to detect affordances in images, at the same time that we quantify the distribution of the aleatoric and epistemic variance at the spatial level. We adapt the Mask-RCNN architecture to learn a probabilistic representation using Monte Carlo dropout. Our results outperform the state-of-the-art of deterministic networks. We attribute this improvement to a better probabilistic feature space repre…
Redesigning the ensemble Kalman filter with a dedicated model of epistemic uncertainty
Warwick Mathematics Institute, University of Warwick（华威大学华威数学研究所）；Division of Mathematical Sciences, Nanyang Technological University（南洋理工大学数学科学学院）；Department of Statistics, University of Warwick（华威大学统计系）
ConformaDecompose: Explaining Uncertainty via Calibration Localization
Department of Computer Science and Engineering, University of Bologna, Italy（博洛尼亚大学计算机科学与工程系）；Marketing and Sales, Automobili Lamborghini S.p.A, Sant'Agata Bolognese, Italy（法拉利拉尔布奇公司）；RCT Data Science and Security, Technical University Dortmund, Germany（多特蒙德技术大学数据科学与安全部）；Jönköping AI Lab, Department of Computing, Jönköping University, Sweden（约翰内斯堡大学人工智能实验室）；Jönköping International Business School, Sweden（约翰内斯堡国际商学院）；Department of Software Engineering, Haliç University, Istanbul, Turkey（伊斯坦布尔哈利奇大学软件工程系）；University College Cork, Ireland（科克大学）
Quantification of Credal Uncertainty: A Distance-Based Approach
Public University of Navarre（纳瓦拉公立大学）；Nanyang Technological University（南洋理工大学）；CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）；LMU Munich（慕尼黑大学）；The University of Manchester（曼彻斯特大学）；Université de Technologie de Compiègne（贡比涅技术大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；German Research Center for Artificial Intelligence (DFKI, DSA)（德国人工智能研究中心）
