论文标题
通过重建错误和基于典型性的罚款止回检测
Out-of-Distribution Detection with Reconstruction Error and Typicality-based Penalty
论文作者
论文摘要
分发（OOD）检测的任务对于实现现实应用程序的安全可靠操作至关重要。在显示了高度的基于似然的检测失败之后，基于\ emph {典型集}的方法吸引了人们的注意。但是，他们仍然没有达到令人满意的表现。首先介绍基于典型性的方法的失败情况，我们提出了采用正常流（NF）的新的基于错误错误的方法。我们进一步引入了基于典型的惩罚，并将其纳入NF的重建误差中，我们提出了一种新的OOD检测方法，即惩罚重建误差（PRE）。由于预测的测试输入属于分布歧管，因此有效地检测了对抗性示例和OOD示例。我们通过使用自然图像数据集，CIFAR-10，Tinyimagenet和ILSVRC2012进行评估来显示我们方法的有效性。
The task of out-of-distribution (OOD) detection is vital to realize safe and reliable operation for real-world applications. After the failure of likelihood-based detection in high dimensions had been shown, approaches based on the \emph{typical set} have been attracting attention; however, they still have not achieved satisfactory performance. Beginning by presenting the failure case of the typicality-based approach, we propose a new reconstruction error-based approach that employs normalizing flow (NF). We further introduce a typicality-based penalty, and by incorporating it into the reconstruction error in NF, we propose a new OOD detection method, penalized reconstruction error (PRE). Because the PRE detects test inputs that lie off the in-distribution manifold, it effectively detects adversarial examples as well as OOD examples. We show the effectiveness of our method through the evaluation using natural image datasets, CIFAR-10, TinyImageNet, and ILSVRC2012.
