论文标题
使用类似于Inpection的自动编码器在图像中基于快速距离的异常检测
Fast Distance-based Anomaly Detection in Images Using an Inception-like Autoencoder
论文作者
论文摘要
检测异常的目的是确定偏离正常行为或预期行为的示例。我们解决图像的问题。我们考虑一种两相方法。首先，使用正常示例，训练了卷积自动编码器（CAE）以提取图像的低维表示。在这里，我们提出了一种新型的建筑选择，当设计CAE（一种类似于凯恩）的CAE。它结合了不同内核大小的卷积过滤器，并使用全球平均池（GAP）操作从CAE的瓶颈层中提取表示形式。其次，我们在图像的学习表示的低维空间中采用了基于距离的异常检测器。但是，我们没有计算确切的距离，而是使用产品量化计算大约距离。这减轻了基于距离的异常检测器的高内存和预测时间成本。我们将我们提出的方法与四个图像数据集的许多基准和最新方法进行了比较，我们发现我们的方法可以提高预测性能。
The goal of anomaly detection is to identify examples that deviate from normal or expected behavior. We tackle this problem for images. We consider a two-phase approach. First, using normal examples, a convolutional autoencoder (CAE) is trained to extract a low-dimensional representation of the images. Here, we propose a novel architectural choice when designing the CAE, an Inception-like CAE. It combines convolutional filters of different kernel sizes and it uses a Global Average Pooling (GAP) operation to extract the representations from the CAE's bottleneck layer. Second, we employ a distanced-based anomaly detector in the low-dimensional space of the learned representation for the images. However, instead of computing the exact distance, we compute an approximate distance using product quantization. This alleviates the high memory and prediction time costs of distance-based anomaly detectors. We compare our proposed approach to a number of baselines and state-of-the-art methods on four image datasets, and we find that our approach resulted in improved predictive performance.
