期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 59, 期 7, 页码 6017-6028出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2020.3013022
关键词
Anomaly detection; Hyperspectral imaging; Generative adversarial networks; Training; Gallium nitride; Image reconstruction; Background-anomaly separability; generative adversarial networks (GANs); hyperspectral anomaly detection
类别
资金
- National Natural Science Foundation of China [61801359, 61571345, 91538101, 61501346, 61502367, 61701360]
- Young Talent Fund of the University Association for Science and Technology in Shaanxi of China [20190103]
- China Postdoctoral Science Foundation [2019T120878, 2017M620440]
- 111 Project [B08038]
- Fundamental Research Funds for the Central Universities [JB180104]
- Natural Science Basic Research Plan in Shaanxi Province of China [2019JQ153, 2016JQ6023, 2016JQ6018]
- Yangtse Rive Scholar Bonus Schemes [CJT160102]
- Ten Thousand Talent Program
- Science and Technology on Electro-Optic Control Laboratory and Aeronautical Science Foundation of China [6142504190206]
This article presents a novel approach using generative adversarial networks (GANs) for separating background and anomaly in hyperspectral anomaly detection. By explicitly constraining the background spectral samples to enhance background reconstruction while weakening anomaly reconstruction, superior background-anomaly separability is achieved.
Hyperspectral images (HSIs) have unique advantages in distinguishing subtle spectral differences of different materials. However, due to complex and diverse backgrounds, unknown prior knowledge, and imbalanced samples, it is challenging to separate background and anomaly. In this article, we present a novel characterization of background-anomaly separability with a generative adversarial network (BASGAN) for hyperspectral anomaly detection. The key contribution is the proposal to explicitly constrain the background and anomaly separability by characterizing background spectral samples while avoiding anomaly reconstruction. First, we use a class saliency map extraction algorithm to obtain pseudobackground and anomaly samples for adversarial training. To further mitigate the suffering of anomaly contamination in background distribution estimation, we introduce background-anomaly separability constrained loss function to enhance the reconstruction of the background while weakening the anomaly reconstruction in a semisupervised way. Additionally, a discriminator is induced into the latent space to make the encoded representation resemble Gaussian distribution during adversarial training. The other is adversarial training in the reconstruction space so that the background estimation can be improved. Experiments conducted on real data sets illustrate the superior background-anomaly separability of the proposed method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据