A Deformable Convolutional Neural Network with Spatial-Channel Attention for Remote Sensing Scene Classification

Di Wang,Jinhui Lan

doi:10.3390/rs13245076

Di Wang, Jinhui Lan

Open Access

PDF Available

https://doi.org/10.3390/rs13245076

Copy DOI

Export

Save

Cite

Journal: Remote Sensing	Publication Date: Dec 14, 2021
Citations: 10	License type: CC BY 4.0

Affiliation: University of Science and Technology Beijing

Abstract
Highlights/Summary
Full-Text PDF
Similar Papers

Abstract

Listen

Remote sensing scene classification converts remote sensing images into classification information to support high-level applications, so it is a fundamental problem in the field of remote sensing. In recent years, many convolutional neural network (CNN)-based methods have achieved impressive results in remote sensing scene classification, but they have two problems in extracting remote sensing scene features: (1) fixed-shape convolutional kernels cannot effectively extract features from remote sensing scenes with complex shapes and diverse distributions; (2) the features extracted by CNN contain a large number of redundant and invalid information. To solve these problems, this paper constructs a deformable convolutional neural network to adapt the convolutional sampling positions to the shape of objects in the remote sensing scene. Meanwhile, the spatial and channel attention mechanisms are used to focus on the effective features while suppressing the invalid ones. The experimental results indicate that the proposed method is competitive to the state-of-the-art methods on three remote sensing scene classification datasets (UCM, NWPU, and AID).

Highlights

Academic Editors: Tais Grippa, Lei Ma, Claudio Persello, ArnaudLe Bris and Jaime ZabalzaReceived: 11 November 2021Accepted: 10 December 2021Published: 14 December 2021Publisher’s Note: MDPI stays neutralWith the development of remote sensing, it is more and more convenient to obtain veryhigh resolution land-cover images, which provides a reliable data source for remote sensing scene classification
To demonstrate the superiority of our proposed method, it is compared with other methods on UCM, including Bidirectional adaptive feature fusion method (BDFF method) [25], Multiscale convolutional neural network (CNN) (MCNN) [37], ResNet with weighted spatial pyramid matching collaborative representation-based classification (ResNet with WSPM-CRC) [38], VGG16 with multi-layer stacked covariance pooling (VGG16 with MSCP) [26], Gated bidirectional network (GBNet) [29], Feature aggregation CNN (FACNN) [39], Scale-free CNN
(SF-CNN) [40], Deep discriminative representation learning with attention map method (DDRL-AM method) [41], and CNN based on attention-oriented multi-branch feature fusion (AMB-CNN) [42]

Summary

Introduction

Academic Editors: Tais Grippa, Lei Ma, Claudio Persello, ArnaudLe Bris and Jaime ZabalzaReceived: 11 November 2021Accepted: 10 December 2021Published: 14 December 2021Publisher’s Note: MDPI stays neutralWith the development of remote sensing, it is more and more convenient to obtain veryhigh resolution land-cover images, which provides a reliable data source for remote sensing scene classification. Academic Editors: Tais Grippa, Lei Ma, Claudio Persello, Arnaud. With the development of remote sensing, it is more and more convenient to obtain veryhigh resolution land-cover images, which provides a reliable data source for remote sensing scene classification. As a basic problem in the field of remote sensing, remote sensing scene classification is widely used in land resources planning [1,2,3,4,5], urban planning [6,7,8], and disaster monitoring [9,10,11]. Remote sensing scene classification has always been a challenging problem because of the following characteristics. With regard to jurisdictional claims in published maps and institutional affil- (2)

Methods

Results

Discussion

Conclusion