This paper studies the classification problem of hyperspectral image (HSI). Inspired by the great success of deep neural networks in Artificial Intelligence (AI), researchers have proposed different deep learning based algorithms to improve the performance of hyperspectral classification. However, deep learning based algorithms always require a large-scale annotated dataset to provide sufficient training. To address this problem, we propose a semi-supervised deep learning framework based on the residual networks (ResNets), which use very limited labeled data supplemented by abundant unlabeled data. The core of our framework is a novel dual-strategy sample selection co-training algorithm, which can successfully guide ResNets to learn from the unlabeled data by making full use of the complementary cues of the spectral and spatial features in HSI classification. Experiments on the benchmark HSI dataset and real HSI dataset demonstrate that, with a small number of training data, our approach achieves competitive performance with maximum improvement of 41% (compare with traditional convolutional neural network (CNN) with 5 initial training samples per class on Indian Pines dataset) for HSI classification as compared with the results from those state-of-the-art supervised and semi-supervised methods.
Fang, B, Li, Y, Zhang, H & Chan, JC-W 2018, 'Semi-Supervised Deep Learning Classification for Hyperspectral Image Based on Dual-Strategy Sample Selection', Remote Sensing, vol. 10, no. 4, 574, pp. 1-23. https://doi.org/10.3390/rs10040574
Fang, B., Li, Y., Zhang, H., & Chan, J. C.-W. (2018). Semi-Supervised Deep Learning Classification for Hyperspectral Image Based on Dual-Strategy Sample Selection. Remote Sensing, 10(4), 1-23. Article 574. https://doi.org/10.3390/rs10040574
@article{562d81345d4941d9acc488f6e78971e3,
title = "Semi-Supervised Deep Learning Classification for Hyperspectral Image Based on Dual-Strategy Sample Selection",
abstract = "This paper studies the classification problem of hyperspectral image (HSI). Inspired by the great success of deep neural networks in Artificial Intelligence (AI), researchers have proposed different deep learning based algorithms to improve the performance of hyperspectral classification. However, deep learning based algorithms always require a large-scale annotated dataset to provide sufficient training. To address this problem, we propose a semi-supervised deep learning framework based on the residual networks (ResNets), which use very limited labeled data supplemented by abundant unlabeled data. The core of our framework is a novel dual-strategy sample selection co-training algorithm, which can successfully guide ResNets to learn from the unlabeled data by making full use of the complementary cues of the spectral and spatial features in HSI classification. Experiments on the benchmark HSI dataset and real HSI dataset demonstrate that, with a small number of training data, our approach achieves competitive performance with maximum improvement of 41% (compare with traditional convolutional neural network (CNN) with 5 initial training samples per class on Indian Pines dataset) for HSI classification as compared with the results from those state-of-the-art supervised and semi-supervised methods.",
keywords = "Co-training, Deep learning, Hyperspectral image classification, Residual networks, Sample selection",
author = "Bei Fang and Ying Li and Haokui Zhang and Chan, {Jonathan Cheung-Wai}",
year = "2018",
month = apr,
day = "8",
doi = "10.3390/rs10040574",
language = "English",
volume = "10",
pages = "1--23",
journal = "Remote Sensing",
issn = "2072-4292",
publisher = "Torrent Valencia: Recent Advances, [2024]-",
number = "4",
}