Next Article in Journal
A Multi-Temporal Object-Based Image Analysis to Detect Long-Lived Shrub Cover Changes in Drylands
Next Article in Special Issue
Remote Sensing and Texture Image Classification Network Based on Deep Learning Integrated with Binary Coding and Sinkhorn Distance
Previous Article in Journal
Winter Wheat Mapping Based on Sentinel-2 Data in Heterogeneous Planting Conditions
Previous Article in Special Issue
Road Extraction of High-Resolution Remote Sensing Images Derived from DenseUNet
Open AccessArticle

Lifting Scheme-Based Deep Neural Network for Remote Sensing Scene Classification

1
Electronic and Information School, Wuhan University, Wuhan 430072, China
2
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
3
School of Computer Science, Wuhan University, Wuhan 430072, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2019, 11(22), 2648; https://doi.org/10.3390/rs11222648
Received: 28 September 2019 / Revised: 8 November 2019 / Accepted: 11 November 2019 / Published: 13 November 2019
Recently, convolutional neural networks (CNNs) achieve impressive results on remote sensing scene classification, which is a fundamental problem for scene semantic understanding. However, convolution, the most essential operation in CNNs, restricts the development of CNN-based methods for scene classification. Convolution is not efficient enough for high-resolution remote sensing images and limited in extracting discriminative features due to its linearity. Thus, there has been growing interest in improving the convolutional layer. The hardware implementation of the JPEG2000 standard relies on the lifting scheme to perform wavelet transform (WT). Compared with the convolution-based two-channel filter bank method of WT, the lifting scheme is faster, taking up less storage and having the ability of nonlinear transformation. Therefore, the lifting scheme can be regarded as a better alternative implementation for convolution in vanilla CNNs. This paper introduces the lifting scheme into deep learning and addresses the problems that only fixed and finite wavelet bases can be replaced by the lifting scheme, and the parameters cannot be updated through backpropagation. This paper proves that any convolutional layer in vanilla CNNs can be substituted by an equivalent lifting scheme. A lifting scheme-based deep neural network (LSNet) is presented to promote network applications on computational-limited platforms and utilize the nonlinearity of the lifting scheme to enhance performance. LSNet is validated on the CIFAR-100 dataset and the overall accuracies increase by 2.48% and 1.38% in the 1D and 2D experiments respectively. Experimental results on the AID which is one of the newest remote sensing scene dataset demonstrate that 1D LSNet and 2D LSNet achieve 2.05% and 0.45% accuracy improvement compared with the vanilla CNNs respectively. View Full-Text
Keywords: scene classification; lifting scheme; convolution; CNN scene classification; lifting scheme; convolution; CNN
Show Figures

Graphical abstract

MDPI and ACS Style

He, C.; Shi, Z.; Qu, T.; Wang, D.; Liao, M. Lifting Scheme-Based Deep Neural Network for Remote Sensing Scene Classification. Remote Sens. 2019, 11, 2648.

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.

Article Access Map by Country/Region

1
Back to TopTop