论文标题
使用辍学贝叶斯神经网络的分配数据检测
Out of Distribution Data Detection Using Dropout Bayesian Neural Networks
论文作者
论文摘要
我们探讨了基于辍学的贝叶斯神经网络（BNN）中包含的信息的实用性，以检测到分布中的数据（OOD）数据。我们首先展示了以前的尝试如何利用辍学BNN的中间层诱导的随机嵌入可能会因使用的距离度量而失败。我们介绍了一种替代方法来测量嵌入不确定性，在理论上证明其使用合理，并证明合并嵌入不确定性如何改善跨三个任务的OOD数据识别：图像分类，语言分类和恶意软件检测。
We explore the utility of information contained within a dropout based Bayesian neural network (BNN) for the task of detecting out of distribution (OOD) data. We first show how previous attempts to leverage the randomized embeddings induced by the intermediate layers of a dropout BNN can fail due to the distance metric used. We introduce an alternative approach to measuring embedding uncertainty, justify its use theoretically, and demonstrate how incorporating embedding uncertainty improves OOD data identification across three tasks: image classification, language classification, and malware detection.
