Exploring Deep Anomaly Detection Methods Based on Capsule Net
Abstract
In this paper, we develop and explore deep anomaly detection techniques based on the capsule network (CapsNet) for image data. Being able to encoding intrinsic spatial relationship between parts and a whole, CapsNet has been applied as both a classifier and deep autoencoder. This inspires us to design a prediction-probability-based and a reconstruction-error-based normality score functions for evaluating the "outlierness" of unseen images. Our results on three datasets demonstrate that the prediction-probability-based method performs consistently well, while the reconstruction-error-based approach is relatively sensitive to the similarity between labeled and unlabeled images. Furthermore, both of the CapsNet-based methods outperform the principled benchmark methods in many cases.
Cite
@article{arxiv.1907.06312,
title = {Exploring Deep Anomaly Detection Methods Based on Capsule Net},
author = {Xiaoyan Li and Iluju Kiringa and Tet Yeap and Xiaodan Zhu and Yifeng Li},
journal= {arXiv preprint arXiv:1907.06312},
year = {2019}
}
Comments
Presented in the "ICML 2019 Workshop on Uncertainty & Robustness in Deep Learning", June 14, Long Beach, California, USA