Variational Autoencoder Anomaly-Detection of Avalanche Deposits in Satellite SAR Imagery
Saumya Sinha, Sophie Giffard‐Roisin, Fatima Karbou, Michaël Deschâtres, Anna Karas, Nicolas Eckert, Cécile Coléou, Claire Monteleoni
Abstract
This work demonstrates that deep unsupervised learning holds much promise for rare event detection, even when labeled data is limited. Rare event detection is challenging for traditional supervised learning approaches due to high class-imbalance. We demonstrate the efficacy of deep unsupervised learning, in particular a variational autoencoder (VAE), when used for anomaly detection, in an application to avalanche detection in the French Alps, from satellite SAR imagery and a limited on-the-ground survey. Remarkably, our results demonstrate that supervision (i.e., access to labeled data) is only needed in the validation phase of our training pipeline, to tune a hyper-parameter: the threshold on reconstruction error of the VAE (trained in an unsupervised fashion) that will be used to designate an observation as an anomaly, i.e., an avalanche in this context.