Deep Anomaly Detection with Outlier Exposure
Deep Anomaly Detection with Outlier Exposure
复制标题
DOI：
--
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
Dan Hendrycks;Mantas Mazeika;Thomas G. Dietterich
中科院分区：
文献类型：
--
作者：
Dan Hendrycks;Mantas Mazeika;Thomas G. Dietterich
在部署机器学习系统时，检测异常输入非常重要。在深度学习中使用更大、更复杂的输入增加了区分异常和分布内示例的难度。与此同时，各种各样的图像和文本数据可供大量使用。我们建议利用这些数据通过训练异常检测器来改进深度异常检测，这种方法我们称之为异常暴露（OE）。这使得异常检测器能够泛化和检测不可见的异常。在自然语言处理和小型和大规模视觉任务的大量实验中，我们发现Outlier Exposure显著提高了检测性能。我们还观察到，在CIFAR-10上训练的尖端生成模型可以为SVHN图像分配比CIFAR-10图像更高的可能性；我们使用OE来缓解这个问题。我们还分析了异常值暴露的灵活性和鲁棒性，并确定了提高性能的辅助数据集的特征。
It is important to detect anomalous inputs when deploying machine learning systems. The use of larger and more complex inputs in deep learning magnifies the difficulty of distinguishing between anomalous and in-distribution examples. At the same time, diverse image and text data are available in enormous quantities. We propose leveraging these data to improve deep anomaly detection by training anomaly detectors against an auxiliary dataset of outliers, an approach we call Outlier Exposure (OE). This enables anomaly detectors to generalize and detect unseen anomalies. In extensive experiments on natural language processing and small- and large-scale vision tasks, we find that Outlier Exposure significantly improves detection performance. We also observe that cutting-edge generative models trained on CIFAR-10 may assign higher likelihoods to SVHN images than to CIFAR-10 images; we use OE to mitigate this issue. We also analyze the flexibility and robustness of Outlier Exposure, and identify characteristics of the auxiliary dataset that improve performance.