MCM-aware Twin-least-square GAN for Hyperspectral Anomaly Detection

Jiaping Zhong, Weiying Xie, Jie Lei, Yunsong Li, Zan Li

Keywords: Multiscale covariance map (MCM), least square loss, hyperspectral anomaly detection, generative adversarial network (GAN)

Abstract: Hyperspectral anomaly detection under high-dimensional data and interference of deteriorated bands without any prior information has been challenging and attracted close attention in the exploration of the unknown in real scenarios. However, some emerging methods based on generative adversarial network (GAN) suffer from the problems of gradient vanishing and training instability with struggling to strike a balance between performance and training sample limitations. In this work, aiming to remedy the drawbacks of existing methods, we present a novel multi-scale covariance map (MCM)-aware twin-least-square GAN (MTGAN). Instead of the widely used single-scale Gaussian hypothesis background estimation, in MTGAN, we introduce the MCM-aware strategy to construct multi-scale priors with precise second-order statistics, thereby implicitly bridging the spatial and spectral information. Thus, we reliably and adaptively represent the prior of HSI to change the priors-lack situation. Moreover, we impose the twin-least-square loss on GAN, which helps improve the generative ability and training stability in feature and image domains, overcoming the gradient vanishing problem. Finally, the network enforced with a new anomaly rejection loss establishes a pure and discriminative background estimation. Experiments demonstrate that the average detection accuracy of MTGAN reaches 0.99809, which is superior to the state-of-the-art algorithms.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: A novel multi-scale covariance map (MCM)-aware twin-least-square GAN (MTGAN) is proposed to solve the problem of insufficient prior, gradient vanishing, and instability training in hyperspectral anomaly detection.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=MG5kxC0ORl