arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.03043cs.CVcs.AIcs.LG
收藏

你的生成模型能检测分布外协变量偏移吗?

Can Your Generative Model Detect Out-of-Distribution Covariate Shift?

Eindhoven University of Technology(埃因霍温理工大学);Philips IGTs(飞利浦IGTs)

Christiaan Viviers, Amaan Valiuddin, Francisco Caetano, Lemar Abdi, Lena Filatova, Peter de With, Fons van der Sommen

AI总结:

本研究针对协变量偏移检测缺乏共识的问题,提出基于条件归一化流的CovariateFlow方法,通过建模高频图像细节检测分布外协变量偏移,在多组数据集上验证了有效性,助力成像系统与OOD检测性能提升。

摘要:

检测分布外(Out-of-Distribution, OOD)传感数据与协变量分布偏移的目标,是识别出与已采集的正常分布内(In-Distribution, ID)集具有不同高层图像统计特性的新测试样本。现有OOD检测研究大多聚焦于语义偏移,对协变量偏移几乎没有共识。生成模型以无监督方式学习ID数据的分布,因此无论下游任务是什么,它们都能有效识别出与所学分布偏差显著的样本。在本研究中,我们通过涉及多种模型的大量分析,阐明了生成模型检测并量化特定领域协变量偏移的能力。为此,我们提出猜想:仅通过建模与信号相关及无关的高频细节,就足以检测大多数常见的传感故障(全局信号统计中的异常与偏差)。我们提出了一种用于OOD检测的新方法CovariateFlow,该方法使用条件归一化流(conditional Normalizing Flows, cNFs),专门针对协变量异方差高频图像分量设计。我们在CIFAR10对比CIFAR10-C、ImageNet200对比ImageNet200-C上的实验结果表明,该方法能准确检测OOD协变量偏移,验证了其有效性。本研究有助于提升成像系统的保真度,并帮助机器学习模型在存在协变量偏移的情况下完成OOD检测。

英文摘要:

Detecting Out-of-Distribution (OOD) sensory data and covariate distribution shift aims to identify new test examples with different high-level image statistics to the captured, normal and In-Distribution (ID) set. Existing OOD detection literature largely focuses on semantic shift with little-to-no consensus over covariate shift. Generative models capture the ID data in an unsupervised manner, enabling them to effectively identify samples that deviate significantly from this learned distribution, irrespective of the downstream task. In this work, we elucidate the ability of generative models to detect and quantify domain-specific covariate shift through extensive analyses that involves a variety of models. To this end, we conjecture that it is sufficient to detect most occurring sensory faults (anomalies and deviations in global signals statistics) by solely modeling high-frequency signal-dependent and independent details. We propose a novel method, CovariateFlow, for OOD detection, specifically tailored to covariate heteroscedastic high-frequency image-components using conditional Normalizing Flows (cNFs). Our results on CIFAR10 vs. CIFAR10-C and ImageNet200 vs. ImageNet200-C demonstrate the effectiveness of the method by accurately detecting OOD covariate shift. This work contributes to enhancing the fidelity of imaging systems and aiding machine learning models in OOD detection in the presence of covariate shift.

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。

↑