Next Article in Journal
A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images
Next Article in Special Issue
Automatic Kernel Size Determination for Deep Neural Networks Based Hyperspectral Image Classification
Previous Article in Journal
Optimized Spectrometers Characterization Procedure for Near Ground Support of ESA FLEX Observations: Part 1 Spectral Calibration and Characterisation
Previous Article in Special Issue
When Low Rank Representation Based Hyperspectral Imagery Classification Meets Segmented Stacked Denoising Auto-Encoder Based Spatial-Spectral Feature
Article Menu
Issue 2 (February) cover image

Export Article

Open AccessTechnical Note
Remote Sens. 2018, 10(2), 290; https://doi.org/10.3390/rs10020290

Remote Sensing Scene Classification Based on Convolutional Neural Networks Pre-Trained Using Attention-Guided Sparse Filters

1
Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China
2
Xi’an Microelectronics Technology Institute, Xi’an 710065, China
3
School of Computer Science and Informatics, De Montfort University, Leicester LE1 9BH, UK
*
Author to whom correspondence should be addressed.
Received: 28 November 2017 / Revised: 3 February 2018 / Accepted: 10 February 2018 / Published: 13 February 2018
View Full-Text   |   Download PDF [9106 KB, uploaded 13 February 2018]   |  

Abstract

Semantic-level land-use scene classification is a challenging problem, in which deep learning methods, e.g., convolutional neural networks (CNNs), have shown remarkable capacity. However, a lack of sufficient labeled images has proved a hindrance to increasing the land-use scene classification accuracy of CNNs. Aiming at this problem, this paper proposes a CNN pre-training method under the guidance of a human visual attention mechanism. Specifically, a computational visual attention model is used to automatically extract salient regions in unlabeled images. Then, sparse filters are adopted to learn features from these salient regions, with the learnt parameters used to initialize the convolutional layers of the CNN. Finally, the CNN is further fine-tuned on labeled images. Experiments are performed on the UCMerced and AID datasets, which show that when combined with a demonstrative CNN, our method can achieve 2.24% higher accuracy than a plain CNN and can obtain an overall accuracy of 92.43% when combined with AlexNet. The results indicate that the proposed method can effectively improve CNN performance using easy-to-access unlabeled images and thus will enhance the performance of land-use scene classification especially when a large-scale labeled dataset is unavailable. View Full-Text
Keywords: scene classification; visual attention mechanism; unsupervised learning; sparse filters; convolutional neural networks scene classification; visual attention mechanism; unsupervised learning; sparse filters; convolutional neural networks
Figures

Graphical abstract

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

Share & Cite This Article

MDPI and ACS Style

Chen, J.; Wang, C.; Ma, Z.; Chen, J.; He, D.; Ackland, S. Remote Sensing Scene Classification Based on Convolutional Neural Networks Pre-Trained Using Attention-Guided Sparse Filters. Remote Sens. 2018, 10, 290.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top