Multilayer Feature Fusion Network With Spatial Attention and Gated Mechanism for Remote Sensing Scene Classification

• Published in: IEEE geoscience and remote sensing letters Vol. 19; pp. 1 - 5
• Main Authors: Meng, Qingyan, Zhao, Maofan, Zhang, Linlin, Shi, Wenxu, Su, Chen, Bruzzone, Lorenzo
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Benchmarks; Calibration; Classification; Convolution; Feature extraction; Feature maps; Fuses; Gated mechanism; Image analysis; Image classification; Logic gates; Machine learning; Methods; Modules; multilayer feature fusion; Multilayers; Neural networks; Nonhomogeneous media; Performance enhancement; Redundancy; Remote sensing; remote sensing (RS); Residual neural networks; scene classification; spatial attention; Spatial calibration
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2022.3173473

Remote sensing (RS) scene classification has attracted extensive attention due to its large number of applications. Recently, convolutional neural network (CNN) methods have shown impressive ability of feature learning in the RS scene classification. However, the performance is still limited by large-scale variance and complex background. To address these problems, we present a multilayer feature fusion network with spatial attention and gated mechanism (MLF2Net_SAGM) for RS scene classification. First, the backbone is employed to extract multilayer convolutional features. Then, a residual spatial attention module (RSAM) is proposed to enhance discriminative regions of the multilayer feature maps, and the key areas can be harvested. Finally, the multilayer spatial calibration features are fused to form the final feature map, and a gated fusion module (GFM) is designed to eliminate feature redundancy and mutual exclusion (FRME). To verify the effectiveness of the proposed method, we conduct comparative experiments based on three widely used RS image scene classification benchmarks. The results show that the direct fusion of multilayer features via element-wise addition leads to FRME, whereas our method fuses multilayer features more effectively and improves the performance of scene classification.