English

OutlierNets: Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection

Sound 2021-04-20 v2 Computer Vision and Pattern Recognition Machine Learning Neural and Evolutionary Computing

Abstract

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.

Keywords

Cite

@article{arxiv.2104.00528,
  title  = {OutlierNets: Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection},
  author = {Saad Abbasi and Mahmoud Famouri and Mohammad Javad Shafiee and Alexander Wong},
  journal= {arXiv preprint arXiv:2104.00528},
  year   = {2021}
}

Comments

7 pages

R2 v1 2026-06-24T00:46:38.855Z