论文标题
用于快速分布和异常检测的子空间建模
Subspace Modeling for Fast Out-Of-Distribution and Anomaly Detection
论文作者
论文摘要
本文提出了一种快速，有原则的方法，用于检测深神经网络（DNN）中异常和分布（OOD）样本。我们建议将线性统计维度降低技术应用于DNN产生的语义特征，以捕获真正由上述特征跨越的低维子空间。我们表明，“特征重建误差”（fre）是$ \ ell_2 $ - 高维空间中原始特征与其低维还原嵌入的预图像之间的差异，对OOD和异常检测非常有效。为了概括到在任何给定层上产生的中间特征，我们通过应用基于非线性核的方法扩展了该方法。使用标准图像数据集和DNN体系结构进行的实验表明，我们的方法符合或超过一流的质量性能，但在最新情况下所需的计算和内存成本的一小部分。即使在传统的CPU上，它也可以非常有效地训练和运行。
This paper presents a fast, principled approach for detecting anomalous and out-of-distribution (OOD) samples in deep neural networks (DNN). We propose the application of linear statistical dimensionality reduction techniques on the semantic features produced by a DNN, in order to capture the low-dimensional subspace truly spanned by said features. We show that the "feature reconstruction error" (FRE), which is the $\ell_2$-norm of the difference between the original feature in the high-dimensional space and the pre-image of its low-dimensional reduced embedding, is highly effective for OOD and anomaly detection. To generalize to intermediate features produced at any given layer, we extend the methodology by applying nonlinear kernel-based methods. Experiments using standard image datasets and DNN architectures demonstrate that our method meets or exceeds best-in-class quality performance, but at a fraction of the computational and memory cost required by the state of the art. It can be trained and run very efficiently, even on a traditional CPU.
