Projected Sliced Wasserstein Autoencoder-based Hyperspectral Images Anomaly Detection

TL;DR

This paper introduces a novel autoencoder-based anomaly detection method for hyperspectral images using Projected Sliced Wasserstein distance, which better captures data manifolds and improves detection accuracy on real-world benchmarks.

Contribution

The paper proposes the PSW autoencoder that employs a weaker Wasserstein-based divergence and an eigen-decomposition approach for efficient high-dimensional data slicing, enhancing anomaly detection.

Findings

Superior performance on hyperspectral anomaly detection benchmarks

Effective in capturing complex data manifolds

Computationally efficient eigen-decomposition method

Abstract

Anomaly detection (AD) has been an active research area in various domains. Yet, the increasing data scale, complexity, and dimension turn the traditional methods into challenging. Recently, the deep generative model, such as the variational autoencoder (VAE), has sparked a renewed interest in the AD problem. However, the probability distribution divergence used as the regularization is too strong, which causes the model cannot capture the manifold of the true data. In this paper, we propose the Projected Sliced Wasserstein (PSW) autoencoder-based anomaly detection method. Rooted in the optimal transportation, the PSW distance is a weaker distribution measure compared with $f$-divergence. In particular, the computation-friendly eigen-decomposition method is leveraged to find the principal component for slicing the high-dimensional data. In this case, the Wasserstein distance can be calculated with the closed-form, even the prior distribution is not Gaussian. Comprehensive experiments conducted on various real-world hyperspectral anomaly detection benchmarks demonstrate the superior performance of the proposed method.