Flow-based Self-supervised Density Estimation for Anomalous Sound Detection
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly DetectionDensity EstimationOut-of-Distribution DetectionUnsupervised Anomaly DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Self-Supervised Robust Scene Flow Estimation via the Alignment of Probability Density Functions
In this paper, we present a new self-supervised scene flow estimation approach for a pair of consecutive point clouds. The key idea of our approach is to represent discrete point clouds as continuous probability density …
Scene Flow EstimationSelf-Supervised LearningSelf-supervised Scene Flow EstimationSupervised Anomaly Detection based on Deep Autoregressive Density Estimators
We propose a supervised anomaly detection method based on neural density estimators, where the negative log likelihood is used for the anomaly score. Density estimators have been widely used for unsupervised anomaly dete…
Anomaly DetectionDensity EstimationSupervised Anomaly DetectionUnsupervised Anomaly DetectionLabel-Free Multivariate Time Series Anomaly Detection
Anomaly detection in multivariate time series (MTS) has been widely studied in one-class classification (OCC) setting. The training samples in OCC are assumed to be normal, which is difficult to guarantee in practical si…
Anomaly DetectionDensity EstimationGraph structure learningOne-Class Classification+3Anomaly Detection in Trajectory Data with Normalizing Flows
The task of detecting anomalous data patterns is as important in practical applications as challenging. In the context of spatial data, recognition of unexpected trajectories brings additional difficulties, such as high …
Anomaly DetectionDensity EstimationCL-Flow:Strengthening the Normalizing Flows by Contrastive Learning for Better Anomaly Detection
In the anomaly detection field, the scarcity of anomalous samples has directed the current research emphasis towards unsupervised anomaly detection. While these unsupervised anomaly detection methods offer convenience, t…
Anomaly DetectionContrastive LearningSelf-Supervised Anomaly DetectionSupervised Anomaly Detection+1