Abstract
Deep learning approaches to anomaly detection have recently improved the state of the art in detection performance on complex datasets such as large collections of images or text. These results have sparked a renewed interest in the anomaly detection problem and led to the introduction of a great variety of new methods. With the emergence of numerous such methods, including approaches based on generative models, one-class classification, and reconstruction, there is a growing need to bring methods of this field into a systematic and unified perspective. In this review we aim to identify the common underlying principles as well as the assumptions that are often made implicitly by various methods. In particular, we draw connections between classic 'shallow' and novel deep approaches and show how this relation might cross-fertilize or extend both directions. We further provide an empirical assessment of major existing methods that is enriched by the use of recent explainability techniques, and present specific worked-through examples together with practical advice. Finally, we outline critical open challenges and identify specific paths for future research in anomaly detection.
Highlights
An anomaly is an observation that deviates considerably from some concept of normality
anomaly detection (AD) is the research area that studies the detection of such anomalous observations through methods, models, and algorithms based on data
We show three canonical one-class classification models (MVE, SVDD, and DSVDD) trained on the Big Moon, Small Moon toy data set, each using a different feature representation, in Fig. 7 for comparison
Summary
This article deals with application of deep learning techniques to anomaly detection. Connections between classic “shallow” and novel deep approaches are established, and it is shown how this relation might cross-fertilize or extend both directions. ABSTRACT | Deep learning approaches to anomaly detection (AD) have recently improved the state of the art in detection performance on complex data sets, such as large. These results have sparked a renewed interest in the AD problem and led to the introduction of a great variety of new methods. We draw connections between classic “shallow” and novel deep approaches and show how this relation might cross-fertilize or extend both directions. KEYWORDS | Anomaly detection (AD); deep learning; explainable artificial intelligence; interpretability; kernel methods; neural networks; novelty detection; one-class classification; outlier detection; out-of-distribution (OOD) detection; unsupervised learning.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have