arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.03390cs.CVcs.LG
收藏

Lightning UQ Box:深度学习不确定性量化的综合框架

Lightning UQ Box: A Comprehensive Framework for Uncertainty Quantification in Deep Learning

Technical University of Munich(慕尼黑工业大学);German Aerospace Center (DLR)(德国航空航天中心);Siemens AG(西门子股份公司);Johns Hopkins University(约翰斯·霍普金斯大学)

Nils Lehmann, Jakob Gawlikowski, Adam J. Stewart, Vytautas Jancauskas, Stefan Depeweg, Eric Nalisnick, Nina Maria Gottschling

AI总结:

本文提出Lightning UQ Box统一框架,集成多种最先进UQ方法,并通过热带气旋风速估计和太阳能板功率预测两个视觉任务进行理论与定量比较,为UQ方法提供基准测试平台。

摘要:

不确定性量化(UQ)是将深度神经网络(DNN)应用于现实世界任务的重要工具,因为它为DNN输出附加了一定程度的置信度。然而,尽管UQ具有诸多益处,但由于应用和评估现有UQ流程需要额外的技术知识,UQ常常被排除在标准DNN工作流程之外。因此,需要一个全面的工具箱,使用户能够将UQ集成到其建模工作流程中,而无需显著额外开销。我们引入了Lightning UQ Box:一个用于应用和评估各种UQ方法的统一接口。在本文中,我们对工具箱中实现的各种最先进的UQ方法进行了理论和定量比较。我们聚焦于两个具有挑战性的视觉任务:(i)从红外卫星图像估计热带气旋风速,以及(ii)从天空的RGB图像估计太阳能电池板的功率输出。通过突出方法之间的差异,我们的结果表明需要一个广泛且易于使用的UQ实验框架,可用于对UQ方法进行基准测试。该工具箱、示例实现和更多信息可在以下网址获取:https://github.com/lightning-uq-box/lightning-uq-box

英文摘要:

Uncertainty quantification (UQ) is an essential tool for applying deep neural networks (DNNs) to real world tasks, as it attaches a degree of confidence to DNN outputs. However, despite its benefits, UQ is often left out of the standard DNN workflow due to the additional technical knowledge required to apply and evaluate existing UQ procedures. Hence there is a need for a comprehensive toolbox that allows the user to integrate UQ into their modelling workflow, without significant overhead. We introduce \texttt{Lightning UQ Box}: a unified interface for applying and evaluating various approaches to UQ. In this paper, we provide a theoretical and quantitative comparison of the wide range of state-of-the-art UQ methods implemented in our toolbox. We focus on two challenging vision tasks: (i) estimating tropical cyclone wind speeds from infrared satellite imagery and (ii) estimating the power output of solar panels from RGB images of the sky. By highlighting the differences between methods our results demonstrate the need for a broad and approachable experimental framework for UQ, that can be used for benchmarking UQ methods. The toolbox, example implementations, and further information are available at: https://github.com/lightning-uq-box/lightning-uq-box

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑