“…A hyperspectral image (HSI) contains hundreds of narrow spectral channels for each pixel, which delivers rich spectral and spatial information [ 1 , 2 , 3 , 4 , 5 ]. Owing to this virtue, HSI has been popularly employed in a considerable number of fields, such as object detection [ 6 , 7 , 8 , 9 ], image classification [ 10 , 11 , 12 , 13 ], and change detection [ 14 , 15 , 16 ]. For all the application fields, hyperspectral anomaly detection, which aims to recognize the outliers whose spectra are significantly different from an ambient scene, has drawn much more attention over the last few years [ 17 ].…”