Utilizing the Score of Data Distribution for Hyperspectral Anomaly Detection

TL;DR

This paper introduces ScoreAD, a hyperspectral anomaly detection method that utilizes the score of data distribution learned by a score-based generative model, effectively identifying outliers based on manifold hypothesis.

Contribution

The paper proposes a novel hyperspectral anomaly detection approach using score-based generative models to leverage the manifold hypothesis for improved detection accuracy.

Findings

Effective detection on four hyperspectral datasets

Outperforms existing anomaly detection methods

Utilizes score-based generative modeling for hyperspectral data

Abstract

Hyperspectral images (HSIs) are a type of image that contains abundant spectral information. As a type of real-world data, the high-dimensional spectra in hyperspectral images are actually determined by only a few factors, such as chemical composition and illumination. Thus, spectra in hyperspectral images are highly likely to satisfy the manifold hypothesis. Based on the hyperspectral manifold hypothesis, we propose a novel hyperspectral anomaly detection method (named ScoreAD) that leverages the time-dependent gradient field of the data distribution (i.e., the score), as learned by a score-based generative model (SGM). Our method first trains the SGM on the entire set of spectra from the hyperspectral image. At test time, each spectrum is passed through a perturbation kernel, and the resulting perturbed spectrum is fed into the trained SGM to obtain the estimated score. The manifold hypothesis of HSIs posits that background spectra reside on one or more low-dimensional manifolds. Conversely, anomalous spectra, owing to their unique spectral signatures, are considered outliers that do not conform to the background manifold. Based on this fundamental discrepancy in their manifold distributions, we leverage a generative SGM to achieve hyperspectral anomaly detection. Experiments on the four hyperspectral datasets demonstrate the effectiveness of the proposed method. The code is available at https://github.com/jiahuisheng/ScoreAD.