arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.05314eess.AScs.LG
收藏

用于无监督异常检测的ID条件自动编码器

ID-Conditioned Auto-Encoder for Unsupervised Anomaly Detection

Samsung R\&D Institute Poland Artificial Intelligence Warsaw, Poland

Sławomir Kapka

摘要:

在本文中,我们介绍了ID条件自动编码器的无监督异常检测。我们的方法是一个适应类条件自动编码器(C2AE)设计的开集识别。假设非异常样本由不同的ID组成,我们应用条件自动编码器,这些ID提供标签。相对于C2AE,我们的方法省略了分类子任务,并将学习过程减少到单次运行。我们通过固定一个常数向量作为不匹配标签的目标来进一步简化学习过程。我们将我们的方法应用于机器状态监测的声音的背景下。我们在DCASE 2020挑战任务2的ToyADMOS和MIMII数据集上评估了我们的方法。我们进行了一项消融研究,以表明我们的方法的哪些步骤对结果影响最大。

英文摘要:

In this paper, we introduce ID-Conditioned Auto-Encoder for unsupervised anomaly detection. Our method is an adaptation of the Class-Conditioned Auto-Encoder (C2AE) designed for the open-set recognition. Assuming that non-anomalous samples constitute of distinct IDs, we apply Conditioned Auto-Encoder with labels provided by these IDs. Opposed to C2AE, our approach omits the classification subtask and reduces the learning process to the single run. We simplify the learning process further by fixing a constant vector as the target for non-matching labels. We apply our method in the context of sounds for machine condition monitoring. We evaluate our method on the ToyADMOS and MIMII datasets from the DCASE 2020 Challenge Task 2. We conduct an ablation study to indicate which steps of our method influences results the most.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑