论文标题
在异常声音检测中学习适应域移动的域移动
Learning to Adapt to Domain Shifts with Few-shot Samples in Anomalous Sound Detection
论文作者
论文摘要
异常检测有许多重要的应用，例如监视工业设备。尽管最近使用深度学习方法在异常检测方面取得了进步，但尚不清楚由于机器负载或环境噪声的变化，例如在分布情况下，现有解决方案将如何执行。我们提出了一个框架，该框架以机器健康监测的应用为基础，该框架适应了很少的样品的新条件。在先前工作的基础上，我们采用了一种基于分类的方法来进行异常检测，并表明了其等效性与正常样品的混合密度估计。我们结合了一个情节训练程序，以匹配推断期间的几杆设置。我们根据元信息定义了多个辅助分类任务，并利用基于梯度的元学习来改善对不同变化的概括。我们在最近发布的不同机器类型的音频测量数据集上评估了我们提出的方法。它在两个基线上提高了10％左右，并且与数据集报道的最佳表现模型相当。
Anomaly detection has many important applications, such as monitoring industrial equipment. Despite recent advances in anomaly detection with deep-learning methods, it is unclear how existing solutions would perform under out-of-distribution scenarios, e.g., due to shifts in machine load or environmental noise. Grounded in the application of machine health monitoring, we propose a framework that adapts to new conditions with few-shot samples. Building upon prior work, we adopt a classification-based approach for anomaly detection and show its equivalence to mixture density estimation of the normal samples. We incorporate an episodic training procedure to match the few-shot setting during inference. We define multiple auxiliary classification tasks based on meta-information and leverage gradient-based meta-learning to improve generalization to different shifts. We evaluate our proposed method on a recently-released dataset of audio measurements from different machine types. It improved upon two baselines by around 10% and is on par with best-performing model reported on the dataset.
