生成式扩散模型以其庞大的参数量（超过1亿）和在图像高维空间中的运作为特征，由于计算需求给传统不确定性估计方法带来了重大挑战。在这项工作中，我们引入了一个创新框架——用于捕获不确定性的扩散集成（Diffusion Ensembles for Capturing Uncertainty, DECU），专为估计扩散模型的认知不确定性而设计。DECU框架引入了一种新方法，通过结合一组静态的预训练参数，高效训练条件扩散模型集成，大幅降低了计算负担和需要训练的参数数量。此外，DECU采用成对距离估计器，通过评估高维空间中模型输出与权重之间的互信息，来准确测量认知不确定性。通过在ImageNet数据集上的实验，展示了该框架的有效性，突出了其捕获认知不确定性的能力，特别是在样本不足的图像类别中。
英文摘要：
Generative diffusion models, notable for their large parameter count (exceeding 100 million) and operation within high-dimensional image spaces, pose significant challenges for traditional uncertainty estimation methods due to computational demands. In this work, we introduce an innovative framework, Diffusion Ensembles for Capturing Uncertainty (DECU), designed for estimating epistemic uncertainty for diffusion models. The DECU framework introduces a novel method that efficiently trains ensembles of conditional diffusion models by incorporating a static set of pre-trained parameters, drastically reducing the computational burden and the number of parameters that require training. Additionally, DECU employs Pairwise-Distance Estimators (PaiDEs) to accurately measure epistemic uncertainty by evaluating the mutual information between model outputs and weights in high-dimensional spaces. The effectiveness of this framework is demonstrated through experiments on the ImageNet dataset, highlighting its capability to capture epistemic uncertainty, specifically in under-sampled image classes.
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）
Hyper-V2X: Hypernetworks for Estimating Epistemic and Aleatoric Uncertainty in Cooperative Bird's-Eye-View Semantic Segmentation
CARISSMA Institute for Electric, COnnected, and Secure Mobility (C-ECOS), Technische Hochschule Ingolstadt（CARISSMA电动、连接与安全移动研究所（C-ECOS）、因戈尔施塔特技术大学）；University of Applied Sciences Aschaffenburg（阿施发堡应用科学大学）
Fujian Agriculture and Forestry University（福建农林大学）；Tianjin University（天津大学）；Minjiang University（闽江学院）；Institute of High Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究所）；Sichuan University（四川大学）；Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局前沿人工智能研究中心（CFAR））
