DeepAI AI Chat
Log In Sign Up

Learning to Adapt to Domain Shifts with Few-shot Samples in Anomalous Sound Detection

by   Bingqing Chen, et al.
Carnegie Mellon University

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 model reported on the dataset.


page 1

page 6


Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection

Neural network-based anomaly detection methods have shown to achieve hig...

LogAnMeta: Log Anomaly Detection Using Meta Learning

Modern telecom systems are monitored with performance and system logs fr...

Disentangling Physical Parameters for Anomalous Sound Detection Under Domain Shifts

To develop a sound-monitoring system for machines, a method for detectin...

First-shot anomaly sound detection for machine condition monitoring: A domain generalization baseline

This paper provides a baseline system for First-shot-compliant unsupervi...

Meta-Learning Based Early Fault Detection for Rolling Bearings via Few-Shot Anomaly Detection

Early fault detection (EFD) of rolling bearings can recognize slight dev...

Few-Shot Bearing Anomaly Detection Based on Model-Agnostic Meta-Learning

The rapid development of artificial intelligence and deep learning techn...