SSDANet: Spectral-Spatial Three-Dimensional Convolutional Neural Network for Hyperspectral Image Classification

doi:10.1109/access.2020.3008029

CIOMP OpenIR

	SSDANet: Spectral-Spatial Three-Dimensional Convolutional Neural Network for Hyperspectral Image Classification
	X. Zhang,Y. C. Wang,N. Zhang,D. D. Xu,H. Y. Luo,B. Chen and G. L. Ben
	2020
发表期刊	Ieee Access
ISSN	2169-3536
卷号	8 页码:127167-127180
摘要	Recently, the classification of hyperspectral images has made great process. Especially, the classification methods based on three-dimensional convolutional neural network have remarkable performance due to the uniqueness of hyperspectral images. However, the hyperspectral classification still faces great challenges due to a series of problems such as the insufficient extraction of spectral-spatial features, the lack of labeled samples, the large amount of noise, the tendency of overfitting and so on. Therefore, SSDANet is proposed to solve the above problems and promote the further development of hyperspectral classification technology based on deep learning. SSDANet is a spectral-spatial three-dimensional convolutional neural network with a deep and wide structure that can significantly improve classification performance. In SSDANet, the spectral-spatial dense connectivity is put forward to protect the integrity of information. It is made up of the spectral branch and the spatial branch, which can learn and reuse the spectral-spatial features. Besides, the spectral-spatial attention mechanism is proposed to adapt the special structure of hyperspectral images. It can excite important spectral-spatial information and suppress unimportant spectral-spatial information. In addition, a series of optimization methods including data augmentation, batch normalization, dropout, exponential decay learning rate, and L2 regularization are adopted to alleviate the problem of overfitting and improve the classification results. To verify the performance of SSDANet, experiments were implemented on two widely used datasets-Pavia University and Indian Pines. Under the condition of limited labeled samples, the classification evaluation indexes of OA, AA, and Kappa on the two datasets all exceeded 99%, reaching state-of-the-art performance.
DOI	10.1109/access.2020.3008029
URL	查看原文
收录类别	SCI ; EI
语种	英语
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/64905
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	X. Zhang,Y. C. Wang,N. Zhang,D. D. Xu,H. Y. Luo,B. Chen and G. L. Ben. SSDANet: Spectral-Spatial Three-Dimensional Convolutional Neural Network for Hyperspectral Image Classification[J]. Ieee Access,2020,8:127167-127180.
APA	X. Zhang,Y. C. Wang,N. Zhang,D. D. Xu,H. Y. Luo,B. Chen and G. L. Ben.(2020).SSDANet: Spectral-Spatial Three-Dimensional Convolutional Neural Network for Hyperspectral Image Classification.Ieee Access,8,127167-127180.
MLA	X. Zhang,Y. C. Wang,N. Zhang,D. D. Xu,H. Y. Luo,B. Chen and G. L. Ben."SSDANet: Spectral-Spatial Three-Dimensional Convolutional Neural Network for Hyperspectral Image Classification".Ieee Access 8(2020):127167-127180.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Zhang-2020-SSDANet_ （2448KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载