Complex-Valued 2D-3D Hybrid Convolutional Neural Network with Attention Mechanism for PolSAR Image Classification

The recently introduced complex-valued convolutional neural network (CV-CNN) has shown considerable advancements for polarimetric synthetic aperture radar (PolSAR) image classification by effectively incorporating both magnitude and phase information. However, a solitary 2D or 3D CNN encounters chal...

Full description

Saved in:
Bibliographic Details
Published inRemote sensing (Basel, Switzerland) Vol. 16; no. 16; p. 2908
Main Authors Li, Wenmei, Xia, Hao, Zhang, Jiadong, Wang, Yu, Jia, Yan, He, Yuhong
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.08.2024
Subjects
Ablation
Agricultural production
Artificial neural networks
attention mechanism
Classification
complex-valued convolutional neural network (CV-CNN)
Computer applications
Decomposition
Eigenvalues
Eigenvectors
Feature extraction
Image classification
Information processing
Machine learning
Neural networks
Object recognition
polarimetric synthetic aperture radar (PolSAR)
Radar imaging
Synthetic aperture radar
Online AccessGet full text

Cover

More Information
Summary:The recently introduced complex-valued convolutional neural network (CV-CNN) has shown considerable advancements for polarimetric synthetic aperture radar (PolSAR) image classification by effectively incorporating both magnitude and phase information. However, a solitary 2D or 3D CNN encounters challenges such as insufficiently extracting scattering channel dimension features or excessive computational parameters. Moreover, these networks’ default is that all information is equally important, consuming vast resources for processing useless information. To address these issues, this study presents a new hybrid CV-CNN with the attention mechanism (CV-2D/3D-CNN-AM) to classify PolSAR ground objects, possessing both excellent computational efficiency and feature extraction capability. In the proposed framework, multi-level discriminative features are extracted from preprocessed data through hybrid networks in the complex domain, along with a special attention block to filter the feature importance from both spatial and channel dimensions. Experimental results performed on three PolSAR datasets demonstrate our present approach’s superiority over other existing ones. Furthermore, ablation experiments confirm the validity of each module, highlighting our model’s robustness and effectiveness.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs16162908