Flow-based Self-supervised Density Estimation for Anomalous Sound Detection
arXiv:2103.08801
Abstract
To develop a machine sound monitoring system, a method for detecting anomalous sound is proposed. Exact likelihood estimation using Normalizing Flows is a promising technique for unsupervised anomaly detection, but it can fail at out-of-distribution detection since the likelihood is affected by the smoothness of the data. To improve the detection performance, we train the model to assign higher likelihood to target machine sounds and lower likelihood to sounds from other machines of the same machine type. We demonstrate that this enables the model to incorporate a self-supervised classification-based approach. Experiments conducted using the DCASE 2020 Challenge Task2 dataset showed that the proposed method improves the AUC by 4.6% on average when using Masked Autoregressive Flow (MAF) and by 5.8% when using Glow, which is a significant improvement over the previous method.
5 pages, 1 figure, accepted in ICASSP 2021
References in corpus (6)
- NICE: Non-linear Independent Components Estimation
- Deep Anomaly Detection with Outlier Exposure
- WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
- Description and Discussion on DCASE2020 Challenge Task2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring
- Normalizing flows for novelty detection in industrial time series data
- Understanding and Mitigating Exploding Inverses in Invertible Neural Networks