Inductive Conformal Out-of-distribution Detection based on Adversarial Autoencoders
Inductive Conformal Out-of-distribution Detection based on Adversarial Autoencoders
复制标题
DOI：
10.1109/coins51742.2021.9524167
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
Feiyang Cai;A. Ozdagli;Nicholas Potteiger;X. Koutsoukos
中科院分区：
文献类型：
--
作者：
Feiyang Cai;A. Ozdagli;Nicholas Potteiger;X. Koutsoukos
机器学习组件广泛用于应对高度不确定环境中的各种复杂任务。然而，分布外 (OOD) 数据可能会导致预测出现较大错误，并显着降低性能。本文首先介绍了不同类型的 OOD 数据，然后提出了一种有效地解决分类问题的 OOD 检测方法。我们的方法利用对抗自动编码器（AAE）来表示训练分布，并利用归纳共形异常检测（ICAD）来在线检测 OOD 高维数据。使用多个数据集的实验结果表明，该方法可以检测各种类型的 OOD 数据，并且误报率较低。而且执行时间很短，可以在线检测。
Machine learning components are used extensively to cope with various complex tasks in highly-uncertain environments. However, Out-Of-Distribution (OOD) data may lead to predictions with large errors and degrade performance considerably. This paper first introduces different types of OOD data and then presents an approach for OOD detection for classification problems efficiently. Our approach utilizes an Adversarial Autoencoder (AAE) for representing the training distribution and Inductive Conformal Anomaly Detection (ICAD) for online detecting OOD high-dimensional data. Experimental results using several datasets demonstrate that the approach can detect various types of OOD data with a small number of false alarms. Moreover, the execution time is very short, allowing for online detection.