Abstract
Anomaly detection of hyperspectral imagery (HSI) identifies the very few samples that do not conform to an intricate background without priors. Despite the extensive success of hyperspectral interpretation techniques based on generative adversarial networks (GANs), applying trained GAN models to hyperspectral anomaly detection remains promising but challenging. Previous generative models can accurately learn the complex background distribution of HSI and typically convert the high-dimensional data back to the latent space to extract features to detect anomalies. However, both background modeling and feature-extraction methods can be improved to become ideal in terms of the modeling power and reconstruction consistency capability. In this work, we present a multi-prior-based network (MPN) to incorporate the well-trained GANs as effective priors to a general anomaly-detection task. In particular, we introduce multi-scale covariance maps (MCMs) of precise second-order statistics to construct multi-scale priors. The MCM strategy implicitly bridges the spectral- and spatial-specific information and fully represents multi-scale, enhanced information. Thus, we reliably and adaptively estimate the HSI label to alleviate the problem of insufficient priors. Moreover, the twin least-square loss is imposed to improve the generative ability and training stability in feature and image domains, as well as to overcome the gradient vanishing problem. Last but not least, the network, enforced with a new anomaly rejection loss, establishes a pure and discriminative background estimation.
Funder
National Natural Science Foundation of China
Subject
General Earth and Planetary Sciences
Reference45 articles.
1. Advances in Hyperspectral Image Classification: Earth Monitoring with Statistical Learning Methods
2. Deep support vector machine for hyperspectral image classification
3. Learning semantic context from normal samples for unsupervised anomaly detection;Yan;Proceedings of the AAAI Conference on Artificial Intelligence (AAAI),2021
4. Latent space autoregression for novelty detection;Abati;Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2019
5. Video summarization via block sparse dictionary selection