JM-Net and cluster-SVM for aerial scene classification

Xiaoqiang Lu, Yuan Yuan, Jie Fang

科研成果: 书/报告/会议事项章节会议稿件同行评审

8 引用 (Scopus)

摘要

Aerial scene classification, which is a fundamental problem for remote sensing imagery, can automatically label an aerial image with a specific semantic category. Although deep learning has achieved competitive performance for aerial scene classification, training the conventional neural networks with aerial datasets will easily stick in overfitting. Because the aerial datasets only contain a few hundreds or thousands images, meanwhile the conventional networks usually contain millions of parameters to be trained. To address the problem, a novel convolutional neural network named Justify Mentioned Net (JM-Net) is proposed in this paper, which has different size of convolution kernels in same layer and ignores the fully convolution layer, so it has fewer parameters and can be trained well on aerial datasets. Additionally, Cluster-SVM, a strategy to improve the accuracy and speed up the classification is used in the specific task. Finally, our method surpass the state-of-art result on the challenging AID dataset while cost shorter time and used smaller storage space.

源语言英语
主期刊名26th International Joint Conference on Artificial Intelligence, IJCAI 2017
编辑Carles Sierra
出版商International Joint Conferences on Artificial Intelligence
2386-2392
页数7
ISBN(电子版)9780999241103
DOI
出版状态已出版 - 2017
已对外发布
活动26th International Joint Conference on Artificial Intelligence, IJCAI 2017 - Melbourne, 澳大利亚
期限: 19 8月 201725 8月 2017

出版系列

姓名IJCAI International Joint Conference on Artificial Intelligence
0
ISSN(印刷版)1045-0823

会议

会议26th International Joint Conference on Artificial Intelligence, IJCAI 2017
国家/地区澳大利亚
Melbourne
时期19/08/1725/08/17

指纹

探究 'JM-Net and cluster-SVM for aerial scene classification' 的科研主题。它们共同构成独一无二的指纹。

引用此