期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 60, 期 -, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2021.3102048
关键词
Image reconstruction; Detectors; Generative adversarial networks; Hyperspectral imaging; Dictionaries; Supervised learning; Convolutional neural networks; Anomaly detection (AD); generative adversarial network (GAN); hyperspectral images (HSIs); sparse coding (SC); weakly supervised learning (WSL)
类别
资金
- National Natural Science Foundation of China [62071360, 61801359, 61571345, 91538101, 61501346, 61502367, 61701360]
- Young Talent fund of 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
This study introduces a sparse coding-inspired generative adversarial network for weakly supervised anomaly detection from hyperspectral images. By integrating a background-category searching step and an SC-inspired regularized network, a robust and interpretable model is developed, which detects anomalies in a latent space.
Anomaly detection (AD) from hyperspectral images (HSIs) is of great importance in both space exploration and Earth observations. However, the challenges caused by insufficient datasets, no labels, and noise corruption substantially downgrade the accuracy of detection. To solve these problems, this article proposes a sparse coding (SC)-inspired generative adversarial network (GAN) for weakly supervised hyperspectral AD (HAD), named sparseHAD. It can learn a discriminative latent reconstruction with small errors for background pixels and large errors for anomalous ones. First, a background-category searching step is built to alleviate the difficulty of data annotation. Then, an SC-inspired regularized network is integrated into an end-to-end GAN to form a weakly supervised spectral mapping model consisting of two encoders, a decoder, and a discriminator. This model not only makes the network more robust and interpretable experimentally and theoretically but also develops a new SC-inspired path for HAD. Subsequently, the proposed sparseHAD detects anomalies in a latent space rather than the original space, which also contributes to its noise robustness. Quantitative assessments and experiments over real HSIs demonstrate the unique promise of the proposed sparseHAD. The code, data, and trained models are available at https://github.com/JiangThea/HAD.
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