Group convolutional neural networks for hyperspectral image classification
- Author
- Xian Li, Mingli Ding and Aleksandra Pizurica (UGent)
- Organization
- Abstract
- Convolutional Neural Network (CNN) has been widely applied in hyperspectral image (HSI) classification exhibiting excellent performance. The CNN model overfitting is a common issue in this domain due to limited amount of labelled training samples. In addition, making the full use of spectral information is still considered an open problem. In this paper, we propose a novel group 2D-CNN model for spectral-spatial classification. Specifically, we propose an original multi-scale spectral feature extraction approach based on a novel concept of multi-kernel depthwise convolution. Furthermore, we exploit for the first time shuffle operation on the group convolutions in HSI spectral-spatial feature extraction to effectively limit the amount of learning parameters. As a result, we design a small and efficient network for HSI classification. Experimental results on real data demonstrate favourable performance compared to the current state-of-the-art.
- Keywords
- SPECTRAL-SPATIAL CLASSIFICATION, Group convolutional neural networks, multi-scale spectral feature extraction, hyperspectral image
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 581.71 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8620279
- MLA
- Li, Xian, et al. “Group Convolutional Neural Networks for Hyperspectral Image Classification.” 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), IEEE, 2019, pp. 639–43, doi:10.1109/ICIP.2019.8803839.
- APA
- Li, X., Ding, M., & Pizurica, A. (2019). Group convolutional neural networks for hyperspectral image classification. 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 639–643. https://doi.org/10.1109/ICIP.2019.8803839
- Chicago author-date
- Li, Xian, Mingli Ding, and Aleksandra Pizurica. 2019. “Group Convolutional Neural Networks for Hyperspectral Image Classification.” In 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 639–43. IEEE. https://doi.org/10.1109/ICIP.2019.8803839.
- Chicago author-date (all authors)
- Li, Xian, Mingli Ding, and Aleksandra Pizurica. 2019. “Group Convolutional Neural Networks for Hyperspectral Image Classification.” In 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 639–643. IEEE. doi:10.1109/ICIP.2019.8803839.
- Vancouver
- 1.Li X, Ding M, Pizurica A. Group convolutional neural networks for hyperspectral image classification. In: 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP). IEEE; 2019. p. 639–43.
- IEEE
- [1]X. Li, M. Ding, and A. Pizurica, “Group convolutional neural networks for hyperspectral image classification,” in 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), Taipei, Taiwan, 2019, pp. 639–643.
@inproceedings{8620279,
abstract = {{Convolutional Neural Network (CNN) has been widely applied in hyperspectral image (HSI) classification exhibiting excellent performance. The CNN model overfitting is a common issue in this domain due to limited amount of labelled training samples. In addition, making the full use of spectral information is still considered an open problem. In this paper, we propose a novel group 2D-CNN model for spectral-spatial classification. Specifically, we propose an original multi-scale spectral feature extraction approach based on a novel concept of multi-kernel depthwise convolution. Furthermore, we exploit for the first time shuffle operation on the group convolutions in HSI spectral-spatial feature extraction to effectively limit the amount of learning parameters. As a result, we design a small and efficient network for HSI classification. Experimental results on real data demonstrate favourable performance compared to the current state-of-the-art.}},
author = {{Li, Xian and Ding, Mingli and Pizurica, Aleksandra}},
booktitle = {{2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)}},
isbn = {{9781538662496}},
issn = {{2381-8549}},
keywords = {{SPECTRAL-SPATIAL CLASSIFICATION,Group convolutional neural networks,multi-scale spectral feature extraction,hyperspectral image}},
language = {{eng}},
location = {{Taipei, Taiwan}},
pages = {{639--643}},
publisher = {{IEEE}},
title = {{Group convolutional neural networks for hyperspectral image classification}},
url = {{http://doi.org/10.1109/ICIP.2019.8803839}},
year = {{2019}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: