Unsupervised Anomaly and Change Detection with Multivariate Gaussianization

TL;DR

This paper introduces an unsupervised, scalable, and parameter-free method for anomaly and change detection in remote sensing images using multivariate Gaussianization, effectively transforming complex data into Gaussian distributions for accurate probability estimation.

Contribution

The paper presents a novel multivariate Gaussianization approach that accurately estimates densities in high-dimensional data, enabling efficient unsupervised anomaly and change detection without hyperparameter tuning.

Findings

Outperforms existing methods in detection power

Robust to high dimensionality and large datasets

Efficient in memory and computational resources

Abstract

Anomaly detection is a field of intense research. Identifying low probability events in data/images is a challenging problem given the high-dimensionality of the data, especially when no (or little) information about the anomaly is available a priori. While plenty of methods are available, the vast majority of them do not scale well to large datasets and require the choice of some (very often critical) hyperparameters. Therefore, unsupervised and computationally efficient detection methods become strictly necessary. We propose an unsupervised method for detecting anomalies and changes in remote sensing images by means of a multivariate Gaussianization methodology that allows to estimate multivariate densities accurately, a long-standing problem in statistics and machine learning. The methodology transforms arbitrarily complex multivariate data into a multivariate Gaussian distribution. Since the transformation is differentiable, by applying the change of variables formula one can estimate the probability at any point of the original domain. The assumption is straightforward: pixels with low estimated probability are considered anomalies. Our method can describe any multivariate distribution, makes an efficient use of memory and computational resources, and is parameter-free. We show the efficiency of the method in experiments involving both anomaly detection and change detection in different remote sensing image sets. Results show that our approach outperforms other linear and nonlinear methods in terms of detection power in both anomaly and change detection scenarios, showing robustness and scalability to dimensionality and sample sizes.