Classifying PolSAR Images Based on Multiview Unsupervised Feature Selection via View-Specific and Cross-View Representations

Multiview features can be acquired from multiple feature extractors or frequency bands to describe polarimetric synthetic aperture radar (PolSAR) images. These multiview features usually have high dimensionality and contain some redundant and irrelevant information leading to classification performance deterioration. Additionally, acquiring label information on PolSAR data is challenging. To resolve these difficulties, we put forward a multiview unsupervised feature selection method via view-specific and cross-view representation (VSCVR) to classify PolSAR images, resulting in retaining the global and local structure of the data and exploring higher order relationships between different views. Specifically, we learn view-specific self-representation with the tensor low-rank constraint for the global structure preservation and exploration of high-order consensus and complementarity between different views. We adopt tensor nuclear norm by tensor singular value decomposition (t-TNN) to achieve the low-rank constraint for multiview self-representation tensor. In addition, we incorporate cross-view common representation with manifold regularization to sustain the local structure information and ensure consistency across multiple views. To accurately describe the local structure, we construct a similarity graph for manifold regularization via the Wishart distance reflecting the statistical property of PolSAR data. Furthermore, a group sparsity constraint is imposed on view-specific projection matrices for feature selection. We propose the corresponding algorithm to handle the VSCVR model and conduct complexity and convergence analysis. Numerical and visual results on some real PolSAR datasets certify that VSCVR can acquire a few important features and improve classification performance effectively.

• Publication year

  2025

• Venue

  IEEE Transactions on Geoscience and Remote Sensing

• Publication date

  Unknown publication date

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1109/TGRS.2025.3558441
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Multiscale adaptive PolSAR image superpixel generation based on local iterative clustering and polarimetric scattering features

  2025cited by this paper
• PolSAR Image Registration Combining Siamese Multiscale Attention Network and Joint Filter

  2024cited by this paper
• Low-Rank Tensor Regularized Graph Fuzzy Learning for Multi-View Data Processing

  2024cited by this paper
• PolSAR Image Registration Using Orientated Gradients of Polarimetric Features

  2024cited by this paper
• A Feature Fusion Network for PolSAR Image Classification Based on Physical Features and Deep Features

  2024cited by this paper
• CNN-Improved Superpixel-to-Pixel Fuzzy Graph Convolution Network for PolSAR Image Classification

  2023cited by this paper
• Nonconvex low-rank tensor approximation with graph and consistent regularizations for multi-view subspace learning

  2023cited by this paper
• Multifrequency PolSAR Image Fusion Classification Based on Semantic Interactive Information and Topological Structure

  2022cited by this paper
• Tensorial Multiview Subspace Clustering for Polarimetric Hyperspectral Images

  2022cited by this paper
• Attention-Based Polarimetric Feature Selection Convolutional Network for PolSAR Image Classification

  2022cited by this paper
• Multi-view unsupervised feature selection with tensor low-rank minimization

  2022influential reference
• Reconstruction Error-Based Decomposition Feature Selection for PolSAR Image

  2022cited by this paper
• Multi-view Unsupervised Feature Selection via Consensus Guided Low-rank Tensor Learning

  2022influential reference
• PolSAR Image Classification Based on Deep Convolutional Neural Networks Using Wavelet Transformation

  2022cited by this paper
• Adaptive Graph Convolutional Network for PolSAR Image Classification

  2021cited by this paper
• Adaptive Similarity Embedding for Unsupervised Multi-View Feature Selection

  2021cited by this paper
• Multilevel projections with adaptive neighbor graph for unsupervised multi-view feature selection

  2021cited by this paper
• Multi-View Feature Selection for PolSAR Image Classification via l₂,₁ Sparsity Regularization and Manifold Regularization

  2021influential reference
• Feature Selective Projection with Low-Rank Embedding and Dual Laplacian Regularization

  2020cited by this paper
• Complex-Valued 3-D Convolutional Neural Network for PolSAR Image Classification

  2020cited by this paper
• PolSAR Feature Extraction Via Tensor Embedding Framework for Land Cover Classification

  2020cited by this paper
• Online Semisupervised Active Classification for Multiview PolSAR Data

  2020cited by this paper
• Hyper-Laplacian Regularized Multilinear Multiview Self-Representations for Clustering and Semisupervised Learning

  2020cited by this paper
• An Online Multiview Learning Algorithm for PolSAR Data Real-Time Classification

  2019cited by this paper
• CNN-Based Polarimetric Decomposition Feature Selection for PolSAR Image Classification

  2019cited by this paper
• Beijing, China

  2019cited by this paper
• Decomposition-Feature-Iterative-Clustering-Based Superpixel Segmentation for PolSAR Image Classification

  2018influential reference
• PolSAR Image Classification Using Polarimetric-Feature-Driven Deep Convolutional Neural Network

  2018cited by this paper
• Supervised Polarimetric SAR Image Classification Using Tensor Local Discriminant Embedding

  2018cited by this paper
• Consensus learning guided multi-view unsupervised feature selection

  2018cited by this paper
• Semi-Supervised Tensorial Locally Linear Embedding for Feature Extraction Using PolSAR Data

  2018cited by this paper
• Integrating color features in polarimetric SAR image classification

  2017cited by this paper
• Local Discriminant Canonical Correlation Analysis for Supervised PolSAR Image Classification

  2017cited by this paper
• Graph self-representation method for unsupervised feature selection

  2017cited by this paper
• Complex-Valued Convolutional Neural Network and Its Application in Polarimetric SAR Image Classification

  2017cited by this paper
• Multi-View Unsupervised Feature Selection with Adaptive Similarity and View Weight

  2017cited by this paper
• Unsupervised Classification of Polarimetirc SAR Image Via Improved Manifold Regularized Low-Rank Representation With Multiple Features

  2017cited by this paper
• On Unifying Multi-view Self-Representations for Clustering by Tensor Multi-rank Minimization

  2016influential reference
• Adaptive multi-view feature selection for human motion retrieval

  2016cited by this paper
• Classification of Polarimetric SAR Images Based on Modeling Contextual Information and Using Texture Features

  2016cited by this paper
• Unsupervised Feature Selection with Structured Graph Optimization

  2016cited by this paper
• Polarimetric SAR Image Classification Using Deep Convolutional Neural Networks

  2016cited by this paper
• Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization

  2016cited by this paper
• Unsupervised feature selection by regularized self-representation

  2015cited by this paper
• Fully Polarimetric SAR Image Classification via Sparse Representation and Polarimetric Features

  2015cited by this paper
• Tensorial Independent Component Analysis-Based Feature Extraction for Polarimetric SAR Data Classification

  2015cited by this paper
• Spectral Clustering ensemble for polarimetric sar classification with Wishart-derived distance and Polarimetric similarity

  2014cited by this paper
• Local Linear Convergence of the Alternating Direction Method of Multipliers on Quadratic or Linear Programs

  2013cited by this paper
• Unsupervised Classification of Fully Polarimetric SAR Images Based on Scattering Power Entropy and Copolarized Ratio

  2013cited by this paper
• Laplacian Eigenmaps-Based Polarimetric Dimensionality Reduction for SAR Image Classification

  2012cited by this paper
• A novel over-segmentation method for polarimetric SAR images classification

  2012cited by this paper
• Robust Recovery of Subspace Structures by Low-Rank Representation

  2010cited by this paper
• Polarimetric Radar Imaging: From Basics to Applications

  2009cited by this paper
• Laplacian Score for Feature Selection

  2005cited by this paper
• Efficient texture analysis of SAR imagery

  2005cited by this paper

• Multiview Manifold Evidential Fusion for PolSAR Image Classification

  2025cites this paper
• EnSSNet: An advanced ensemble self-supervised learning framework with mini batch-graph convolutional network and deep curriculum learning for robust PolSAR image classification

  2025cites this paper