OutlierNets: Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection
This enables on-device anomaly detection for factory maintenance, addressing computational resource constraints, though it is incremental in optimizing existing methods for efficiency.
The paper tackles the problem of deploying deep learning for acoustic anomaly detection in industrial settings by developing highly compact autoencoder networks, achieving detection accuracy comparable to larger models with as few as 686 parameters and up to 21x lower latency.
Human operators often diagnose industrial machinery via anomalous sounds. Automated acoustic anomaly detection can lead to reliable maintenance of machinery. However, deep learning-driven anomaly detection methods often require an extensive amount of computational resources which prohibits their deployment in factories. Here we explore a machine-driven design exploration strategy to create OutlierNets, a family of highly compact deep convolutional autoencoder network architectures featuring as few as 686 parameters, model sizes as small as 2.7 KB, and as low as 2.8 million FLOPs, with a detection accuracy matching or exceeding published architectures with as many as 4 million parameters. Furthermore, CPU-accelerated latency experiments show that the OutlierNet architectures can achieve as much as 21x lower latency than published networks.