Frequency‐to‐spectrum mapping GAN for semisupervised hyperspectral anomaly detection

作     者：Degang Wang Lianru Gao Ying Qu Xu Sun Wenzhi Liao 

作者机构：Key Laboratory of Computational Optical Imaging TechnologyAerospace Information Research InstituteChinese Academy of SciencesBeijingChina College of Resources and EnvironmentUniversity of Chinese Academy of SciencesBeijingChina Faculty of Geographical ScienceBeijing Normal UniversityBeijingChina Flanders MakeLommelBelgium Ghent UniversityGhentBelgium 

出 版 物：《CAAI Transactions on Intelligence Technology》 (智能技术学报（英文）)

年 卷 期：2023年第8卷第4期

页      面：1258-1273页

核心收录：

学科分类：0710[理学-生物学] 07[理学] 0804[工学-仪器科学与技术] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 070101[理学-基础数学] 

基　　金：supported by the National Natural Science Foundation of China under Grant 62161160336 Grant 41871245 in part by the Belgium Vlaio project(AI ICON‐2021‐0599:Smart industrial spectral cameras via artificial intelligence) 

主　　题：deep learning generative adversarial network hyperspectral image neural network semisupervised learning 

摘      要：Most unsupervised or semisupervised hyperspectral anomaly detection(HAD)methods train background reconstruction models in the original spectral ***,due to the noise and spatial resolution limitations,there may be a lack of discrimination between backgrounds and *** makes it easy for the autoencoder to capture the lowlevel features shared between the two,thereby increasing the difficulty of separating anomalies from the backgrounds,which runs counter to the purpose of *** this end,the authors map the original spectrums to the fractional Fourier domain(FrFD)and reformulate it as a mapping task in which restoration errors are employed to distinguish background and *** study proposes a novel frequency‐to‐spectrum mapping generative adversarial network for ***,the depth separable features of backgrounds and anomalies are enhanced in the *** to the semisupervised approach,FTSGAN needs to learn the embedded features of the backgrounds,thus mapping and restoring them from the FrFD to the original spectral *** strategy effectively prevents the model from focussing on the numerical equivalence of input and output,and restricts the ability of FTSGAN to restore *** comparison and analysis of the experiments verify that the proposed method is competitive.