Center-Aware Adversarial Autoencoder for Anomaly Detection
- 9 November 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 33 (6) , 2480-2493
Abstract
Anomaly detection based on subspace learning has attracted much attention, in which the compactness of subspace is commonly considered as the core concern. Most related studies directly optimize the distance from the subspace representation to the fixed center, and the influence of the anomaly level of each normal sample is not considered to adjust the normal concentrated areas. In such cases, it is difficult to isolate the normal areas from the anomaly ones by making the subspace compact. To this end, we propose a center-aware adversarial autoencoder (CA-AAE) method, which detects anomaly samples by acquiring more compact and discriminative subspace representations. To fully exploit the subspace information to improve the compactness, anomaly-level description and feature learning are novelly integrated herein by dividing the output space of the encoder into presubspace and postsubspace. In presubspace, the toward-center prior distribution is imposed by the adversarial learning mechanism, and the anomaly level of normal samples can be described from a probabilistic perspective. In postsubspace, a novel center-aware strategy is established to enhance the compactness of the postsubspace, which achieves adaptive adjustment of the normal areas by constructing a weighted center based on the anomaly level. Then, a flexible anomaly score function is constructed in the testing stage, in which both the toward-center loss and the reconstruction loss are combined to balance the information in the learned subspace and the original space. Compared to other related methods, the proposed CA-AAE shows the effectiveness and advantages in numerical experiments.Keywords
Funding Information
- National Science and Technology Innovation 2030 Major Project of the Ministry of Science and Technology of China (2018AAA0101604)
This publication has 36 references indexed in Scilit:
- Improved principal component analysis for anomaly detection: Application to an emergency departmentComputers & Industrial Engineering, 2015
- Robust Structured Subspace Learning for Data RepresentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- A review of novelty detectionSignal Processing, 2014
- Anomaly detectionACM Computing Surveys, 2009
- Wilcoxon Signed‐Rank Test2008
- Kernel PCA for novelty detectionPattern Recognition, 2007
- Support Vector Data DescriptionMachine Learning, 2004
- Estimating the Support of a High-Dimensional DistributionNeural Computation, 2001
- Content-based image retrieval at the end of the early yearsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000