arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12967cs.LGstat.ML
收藏

深度神经网络中有效分布外检测的统计框架

A statistical framework for efficient out of distribution detection in deep neural networks

Technion(以色列理工学院);Habana Labs - An Intel company(Habana实验室——英特尔旗下公司);Tel Aviv University(特拉维夫大学)

Matan Haroush, Tzviel Frostig, Ruth Heller, Daniel Soudry

摘要:

背景通常,深度神经网络(DNN)可以很好地概括从与训练集相似的分布中提取的样本。然而,当测试样本来自不同的分布时,DNN的预测是脆弱和不可靠的。这是在现实世界应用中部署的一个主要问题,其中这种行为可能会带来相当大的成本,例如工业生产线,自动驾驶汽车或医疗保健应用。捐款.我们将DNN中的分布外(OOD)检测视为统计假设检验问题。在我们提出的框架内生成的测试结合了来自整个网络的证据。与以前的OOD检测方法不同,这个框架为每个测试样本返回一个$p$值。保证保持测试数据的I类错误(T1 E-错误预测实际分销样品的OOD)。此外,这允许在保持T1 E的同时组合多个检测器。在此框架的基础上,我们提出了一种新的面向对象的过程的基础上低阶统计。我们的方法在公认的OOD基准测试上取得了与最先进的方法相当或更好的结果,而无需重新训练网络参数或假设测试分布的先验知识-并且计算成本仅为计算成本的一小部分。

英文摘要:

Background. Commonly, Deep Neural Networks (DNNs) generalize well on samples drawn from a distribution similar to that of the training set. However, DNNs' predictions are brittle and unreliable when the test samples are drawn from a dissimilar distribution. This is a major concern for deployment in real-world applications, where such behavior may come at a considerable cost, such as industrial production lines, autonomous vehicles, or healthcare applications. Contributions. We frame Out Of Distribution (OOD) detection in DNNs as a statistical hypothesis testing problem. Tests generated within our proposed framework combine evidence from the entire network. Unlike previous OOD detection heuristics, this framework returns a $p$-value for each test sample. It is guaranteed to maintain the Type I Error (T1E - incorrectly predicting OOD for an actual in-distribution sample) for test data. Moreover, this allows to combine several detectors while maintaining the T1E. Building on this framework, we suggest a novel OOD procedure based on low-order statistics. Our method achieves comparable or better results than state-of-the-art methods on well-accepted OOD benchmarks, without retraining the network parameters or assuming prior knowledge on the test distribution -- and at a fraction of the computational cost.

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。

↑