arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.08443cs.LG
收藏

基于Stiefel限制核机器的无监督能量分布外检测

Unsupervised Energy-based Out-of-distribution Detection using Stiefel-Restricted Kernel Machine

KU Leuven(鲁汶大学)

Francesco Tonin, Arun Pandey, Panagiotis Patrinos, Johan A. K. Suykens

摘要:

检测分发外(OOD)样本是在现实世界中部署机器学习系统的基本要求。到目前为止,对基于能量的OOD检测器的研究主要集中在来自可访问类标签的预训练神经网络分类器的softmax置信度分数上。相比之下,我们提出了一个无监督的基于能量的OOD检测器,利用Stiefel限制内核机(St-RKM)。训练需要最小化具有自动编码器损失项和RKM能量的目标函数,其中互连矩阵位于Stiefel流形上。此外,我们概述了多个能量函数的定义的基础上RKM框架,并讨论其效用。在标准数据集上的实验中,该方法改进了现有的基于能量的OOD检测器和深度生成模型。通过几个烧蚀研究,我们进一步说明了每一个建议的能量函数的优点上OOD检测性能。

英文摘要:

Detecting out-of-distribution (OOD) samples is an essential requirement for the deployment of machine learning systems in the real world. Until now, research on energy-based OOD detectors has focused on the softmax confidence score from a pre-trained neural network classifier with access to class labels. In contrast, we propose an unsupervised energy-based OOD detector leveraging the Stiefel-Restricted Kernel Machine (St-RKM). Training requires minimizing an objective function with an autoencoder loss term and the RKM energy where the interconnection matrix lies on the Stiefel manifold. Further, we outline multiple energy function definitions based on the RKM framework and discuss their utility. In the experiments on standard datasets, the proposed method improves over the existing energy-based OOD detectors and deep generative models. Through several ablation studies, we further illustrate the merit of each proposed energy function on the OOD detection performance.

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。

↑