Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
复制标题
DOI：
--
复制
发表时间：
2019-03
期刊：
影响因子：
--
通讯作者：
Chieh-Hsin Lai;Dongmian Zou;Gilad Lerman
中科院分区：
文献类型：
--
作者：
Chieh-Hsin Lai;Dongmian Zou;Gilad Lerman
我们提出了一个神经网络的无监督异常检测与一个新的强大的子空间恢复层（RSR层）。该层试图从给定数据的潜在表示中提取底层子空间，并删除远离该子空间的离群值。它在自动编码器中使用。编码器将数据映射到潜在空间中，RSR层从潜在空间中提取子空间。解码器然后平滑地将底层子空间映射回接近原始内点的“流形”。根据原始位置和映射位置之间的距离区分内点和离群点（内点小，离群点大）。使用图像和文档数据集进行的大量数值实验证明了最先进的精确度和召回率。
We propose a neural network for unsupervised anomaly detection with a novel robust subspace recovery layer (RSR layer). This layer seeks to extract the underlying subspace from a latent representation of the given data and removes outliers that lie away from this subspace. It is used within an autoencoder. The encoder maps the data into a latent space, from which the RSR layer extracts the subspace. The decoder then smoothly maps back the underlying subspace to a "manifold" close to the original inliers. Inliers and outliers are distinguished according to the distances between the original and mapped positions (small for inliers and large for outliers). Extensive numerical experiments with both image and document datasets demonstrate state-of-the-art precision and recall.