RADC-Net: A residual attention based convolution network for aerial scene classification

• Published in: Neurocomputing (Amsterdam) 2020-02, Vol.377, p.345-359
• Main Authors: Bi, Qi, Qin, Kun, Zhang, Han, Li, Zhili, Xu, Kai
• Format: Article
• Language: English
• Subjects: Aerial image; Convolutional neural network (CNN); Dense connection; Enhanced classification layer; Residual attention
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2019.11.068

With rapid development of satellite and airplane platforms, aerial image has become more and more accessible. Aerial image scene classification plays an important role in many remote sensing and geo-science applications. Deep learning methods, especially convolutional neural network (CNN), have boosted the performance of aerial image scene classification significantly because of the strong feature representation ability. However, the distribution of geo-spatial objects and the spatial arrangement of aerial image scenes is often more complicated than natural image scenes. While current CNNs usually highlight the global semantics, more local semantics and more discriminative features need to be preserved to deal with the aforementioned challenges in aerial scenes. In this paper, we propose a residual attention based dense connected convolutional neural network (RADC-Net) to tackle this problem. This framework contains three dense block each followed by an attention block and an enhanced classification layer. Firstly, we simplify the current dense connection structure so that our dense block has much fewer parameters while maintaining discriminative convolutional feature representation ability. Then, we propose a novel residual attention block for our framework to highlight the local semantics relevant to the aerial scenes. Finally, we introduce an enhanced classification layer in our framework to further refine the extracted convolutional features and highlight local semantic information. We comprehensively evaluate the performance of our proposed RADC-Net on three publicly available benchmark datasets. Experimental results demonstrate that our proposed RADC-Net outperforms some state-of-the-art methods with much fewer parameters.