A full convolutional network based on DenseNet for remote sensing scene classification
Top Cited Papers
Open Access
- 1 January 2019
- journal article
- research article
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Biosciences and Engineering
- Vol. 16 (5), 3345-3367
- https://doi.org/10.3934/mbe.2019167
Abstract
The convolutional neural networks (CNN) applied in remote sensing scene classification have two common problems. One is that these models have large number of parameters, which causes over-fitting easily. The other is that the network is not deep enough, thus more abstract semantic information cannot be extracted. To solve these two problems, we propose a simple and efficient full convolutional network based on DenseNet for remote sensing scene classification. We construct a small number of convolutional kernels to generate a large number of reusable feature maps by dense connections, which makes the network deeper, but does not increase the number of parameters significantly. Our network is so deep that it has more than 100 layers. However, it has only about 7 million parameters, which is far less than the number of VGGos parameters. Then we incorporate an adaptive average 3D pooling operation in our network. This operation fixes feature maps of size 7 × 7 from the last DenseBlock to 1 × 1 and decreases the number of channels from 1024 to 512, thus the whole network can accept input images with different sizes. Furthermore, we design the convolutional layer instead of the fully connected layer that is used as a classifier usually, so that the output features of the network can be classified without flattening operation, which simplifies the classification operation. Finally, a good model is trained by exploiting pre-trained weights and data augmentation technology. Compared with several state-of-the-art algorithms, our algorithm improves classification performance significantly on UCM dataset, AID dataset, OPTIMAL-31 dataset and NWPU-RESISC45 dataset.Keywords
This publication has 33 references indexed in Scilit:
- Remote Sensing Image Scene Classification Using Multi-Scale Completed Local Binary Patterns and Fisher VectorsRemote Sensing, 2016
- Comparison of approximation methods to Kullback–Leibler divergence between Gaussian mixture models for satellite image retrievalRemote Sensing Letters, 2016
- Semantic Annotation of High-Resolution Satellite Images via Weakly Supervised LearningIEEE Transactions on Geoscience and Remote Sensing, 2016
- Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing ImageryRemote Sensing, 2015
- Scene Classification via a Gradient Boosting Random Convolutional Network FrameworkIEEE Transactions on Geoscience and Remote Sensing, 2015
- Multiview Deep Learning for Land-Use ClassificationIEEE Geoscience and Remote Sensing Letters, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Measuring the Effectiveness of Various Features for Thematic Information Extraction From Very High Resolution Remote Sensing ImageryIEEE Transactions on Geoscience and Remote Sensing, 2015
- Block-based semantic classification of high-resolution multispectral aerial imagesSignal, Image and Video Processing, 2014
- Extreme value theory-based calibration for the fusion of multiple features in high-resolution satellite scene classificationInternational Journal of Remote Sensing, 2013