论文标题
在深度异常检测中重新思考假设
Rethinking Assumptions in Deep Anomaly Detection
论文作者
论文摘要
尽管可以将异常检测（AD）视为分类问题（名义与异常），通常以无监督的方式进行治疗，因为通常没有一个人可以访问或使用它是不可避免的数据集，该数据集是一个充分表征“异常”含义的足够表征的数据集。在本文中，我们提出结果表明，这种直觉似乎并没有扩展到图像上的深度广告。对于最新的ImageNet上的AD基准测试，经过培训的分类器可以辨别正常样品，并且只有几个（64）随机自然图像能够比Deep AD中的当前状态胜过当前的现状。在实验上，我们发现图像数据的多尺度结构使示例异常具有异常信息。
Though anomaly detection (AD) can be viewed as a classification problem (nominal vs. anomalous) it is usually treated in an unsupervised manner since one typically does not have access to, or it is infeasible to utilize, a dataset that sufficiently characterizes what it means to be "anomalous." In this paper we present results demonstrating that this intuition surprisingly seems not to extend to deep AD on images. For a recent AD benchmark on ImageNet, classifiers trained to discern between normal samples and just a few (64) random natural images are able to outperform the current state of the art in deep AD. Experimentally we discover that the multiscale structure of image data makes example anomalies exceptionally informative.
