학술논문
A New Autoencoder Training Paradigm for Unsupervised Hyperspectral Anomaly Detection
Document Type
Conference
Author
Source
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Geoscience and Remote Sensing Symposium, IGARSS 2020 - 2020 IEEE International. :3967-3970 Sep, 2020
Subject
Language
ISSN
2153-7003
Abstract
We introduce new methods for training an autoencoder (AE) as an unsupervised hyperspectral anomaly detector. We detail a new percentile loss (PL) that reliably constructs an accurate background model while limiting the erroneous inclusion of anomalous pixels. We also improve detection performance and reliability by introducing a cumulative detection score that incorporates statistics calculated from the ensemble of AE models generated over the history of the training process. We show improved detection performance on two data sets relative to two baseline algorithms.