Abstract
The majority of existing hyperspectral anomaly detection (HAD) methods use the low-rank representation (LRR) model to separate the background and anomaly components, where the anomaly component is optimized by handcrafted sparse priors (e.g., $\ell_{2,1}$-norm). However, this may not be ideal since they overlook the spatial structure present in anomalies and make the detection result largely dependent on manually set sparsity. To tackle these problems, we redefine the optimization criterion for the anomaly component in the LRR model with a self-supervised network called self-supervised anomaly prior (SAP). This prior is obtained by the pretext task of self-supervised learning, which is customized to learn the characteristics of hyperspectral anomalies. Specifically, this pretext task is a classification task to distinguish the original hyperspectral image (HSI) and the pseudo-anomaly HSI, where the pseudo-anomaly is generated from the original HSI and designed as a prism with arbitrary polygon bases and arbitrary spectral bands. In addition, a dual-purified strategy is proposed to provide a more refined background representation with an enriched background dictionary, facilitating the separation of anomalies from complex backgrounds. Extensive experiments on various hyperspectral datasets demonstrate that the proposed SAP offers a more accurate and interpretable solution than other advanced HAD methods.
Abstract (translated)
目前大多数超分辨率异常检测(HAD)方法使用低秩表示(LRR)模型将背景和异常成分进行分离,其中异常成分通过手工构建稀疏先验(例如,$\ell_{2,1}$范数)进行优化。然而,这可能不是理想的,因为它们忽视了异常中的空间结构,并将检测结果的准确性很大程度上依赖于人为设置的稀疏性。为了解决这些问题,我们通过自监督网络重新定义了LRR模型中异常成分的优化准则,称为自监督异常先验(SAP)。这一先验是通过自监督学习的预处理任务获得的,该任务专门用于学习超分辨率异常的特征。具体来说,这一预处理任务是一种分类任务,用于区分原始超分辨率图像(HSI)和伪异常HSI,其中伪异常是从原始HSI生成的,并设计为一个具有任意多边形基和任意频带的棱镜。此外,我们提出了一个双净化策略,以提供具有丰富背景字典的更精细的背景表示,促进异常与复杂背景的分离。在各种超分辨率数据集上进行的大量实验证明,与其它高级HAD方法相比,所提出的SAP具有更准确和可解释的解决方案。
URL
https://arxiv.org/abs/2404.13342