Towards better exploiting convolutional neural networks for remote sensing scene classification
详细信息 查看全文
- 作者：Keiller Nogueiraa ; keiller.nogueira@dcc.ufmg.br" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Otá ; vio A.B. Penattib ; o.penatti@samsung.com" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Jefersson A. dos Santosa ; jefersson@dcc.ufmg.br" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Deep learning ; Convolutional neural networks ; Fine-tune ; Feature extraction ; Aerial scenes ; Hyperspectral images ; Remote sensing
- 刊名：Pattern Recognition
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：61
- 期：Complete
- 页码：539-556
- 全文大小：4521 K
文摘
- •
Analysis of the generalization power of ConvNets for remote sensing datasets.
- •
Comparative analysis of ConvNets and low-level and mid-level feature descriptors.
- •
Evaluation and analysis of three strategies to exploit existing ConvNets in different scenarios.
- •
Evaluation of ConvNets with state-of-the-art baselines.