Hyperspectral anomaly detection with self-supervised anomaly prior

Yidan Liu, Kai Jiang, Weiying Xie, Jiaqing Zhang, Yunsong Li, Leyuan Fang

Abstract: Highlights•First study using DNN to obtain anomaly priors, independent of manual parameters.•Developed a novel LRR model with self-supervised priors.•Proposed a dual-purified strategy to refine background representation.