Neural Transformation Learning for Deep Anomaly Detection Beyond Images-猫眼课题宝

DOI：

发表时间：

2021-03

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Chen Qiu;Timo Pfrommer;M. Kloft;S. Mandt;Maja R. Rudolph

数据转换（例如旋转、反射和裁剪）在自监督学习中起着重要作用。通常，图像被转换为不同的视图，在涉及这些视图的任务上训练的神经网络为下游任务（包括异常检测）产生有用的特征表示。然而，对于图像数据之外的异常检测，通常不清楚使用哪些变换。在这里，我们提出了一个简单的端到端的异常检测过程与可学习的转换。其关键思想是将转换后的数据嵌入到语义空间中，使得转换后的数据仍然类似于其未转换的形式，而不同的转换很容易区分。时间序列上的大量实验表明，我们提出的方法优于现有的方法，在一个与。休息设置，并在更具挑战性的n-vs中具有竞争力。其余异常检测任务。在来自医疗和网络安全领域的表格数据集上，我们的方法学习特定于领域的转换，并比以前的工作更准确地检测异常。

Data transformations (e.g. rotations, reflections, and cropping) play an important role in self-supervised learning. Typically, images are transformed into different views, and neural networks trained on tasks involving these views produce useful feature representations for downstream tasks, including anomaly detection. However, for anomaly detection beyond image data, it is often unclear which transformations to use. Here we present a simple end-to-end procedure for anomaly detection with learnable transformations. The key idea is to embed the transformed data into a semantic space such that the transformed data still resemble their untransformed form, while different transformations are easily distinguishable. Extensive experiments on time series demonstrate that our proposed method outperforms existing approaches in the one-vs.-rest setting and is competitive in the more challenging n-vs.-rest anomaly detection task. On tabular datasets from the medical and cyber-security domains, our method learns domain-specific transformations and detects anomalies more accurately than previous work.

Neural Transformation Learning for Deep Anomaly Detection Beyond Images

文献摘要

相似文献