• Home
  • Search
  • Statistical Scattering Component-Based Subspace Alignment for Unsupervised Cross-Domain PolSAR Image Classification
  • Cite Icon27
  • https://doi.org/10.1109/tgrs.2020.3028906Copy DOI Icon

Statistical Scattering Component-Based Subspace Alignment for Unsupervised Cross-Domain PolSAR Image Classification

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Increasing amounts of polarimetric synthetic aperture radar (PolSAR) images from different sensors covering different scenes are available, but limited labeled samples and trained models can hardly work well in these cross-domain data interpretations. Fortunately, domain adaptation (DA) can transfer knowledge in existing images to new yet related images. DA shows attractive potential for PolSAR classification, and it is still challenging due to more complex domain shifts caused by different sensors, imaging conditions, and distributions. Inspired by the widely applicable polarimetric scattering mechanisms and DA ability of subspace alignment (SA), this article is devoted to constructing a robust unsupervised cross-domain PolSAR classification framework, by exploring scattering and statistical characteristics mapping between the source and target domains. First, classical scattering components of both source and target data were extracted, and Wishart clustering was adopted to derive the statistical information of scattering components at patch level. Second, the intrinsic polarimetric scattering components were estimated and extracted, which were called statistical scattering components (SSCs). Third, by applying SA, the source SSC was aligned with target SSC, and domain shift was further reduced. Finally, the target PolSAR image was classified based on labeled samples from source domain, and unsupervised cross-domain classification was achieved by SSC-based SA (SSC-SA). The unsupervised cross-domain experiments are conducted on 49 units among 11 data sets, including Radarsat-2, Gaofen-3, AIRSAR, and Pi-SAR images. With randomly selected labeled samples (about 2%–10%) from source domain, the accuracies of the proposed cross-domain classifications range between 80.20% and 95.64%. Also, the proposed SSC feature pattern is proved extensible for other polarimetric basis and decompositions.

Similar Papers
  • Research Article
  • Citations33

A General Feature Paradigm for Unsupervised Cross-Domain PolSAR Image Classification

  • Apr 29, 2021
  • IEEE Geoscience and Remote Sensing Letters
  • Rong Gui +5
  • PDF
  • Research Article
  • Citations11

A Polarimetric Scattering Characteristics-Guided Adversarial Learning Approach for Unsupervised PolSAR Image Classification

  • Mar 27, 2023
  • Remote Sensing
  • Hongwei Dong +6
  • Conference Article

Unsupervised Cross-Domain Network Based on Bi-classifier for PolSAR Image Classification

  • Sep 22, 2023
  • Wenqiang Hua +3
  • Research Article
  • Citations1

Unsupervised Cross-Domain Polarimetric Synthetic Aperture Radar (PolSAR) Change Monitoring Based on Limited-Label Transfer Learning and Vision Transformer

  • May 20, 2025
  • Remote Sensing
  • Xinyue Zhang +5
  • Research Article
  • Citations40

Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework

  • Sep 10, 2019
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Lamei Zhang +2
  • PDF
  • Research Article
  • Citations13

Semi-Supervised Classification of PolSAR Images Based on Co-Training of CNN and SVM with Limited Labeled Samples.

  • Feb 13, 2023
  • Sensors
  • Mingjun Zhao +4
  • PDF
  • Research Article
  • Citations6

Multiple Classifiers Based Semi-Supervised Polarimetric SAR Image Classification Method

  • Apr 25, 2021
  • Sensors (Basel, Switzerland)
  • Lekun Zhu +3
  • Research Article

Knowledge and data co-driven deep learning model for PolSAR image classification

  • Mar 01, 2026
  • Results in Engineering
  • Wenqiang Hua +2
  • PDF
  • Research Article
  • Citations13

Eigenvalue Statistical Components-Based PU-Learning for PolSAR Built-Up Areas Extraction and Cross-Domain Analysis

  • Jan 01, 2020
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Rong Gui +4
  • Research Article
  • Citations15

PolSAR image classification using complex-valued multiscale attention vision transformer (CV-MsAtViT)

  • Mar 01, 2025
  • International Journal of Applied Earth Observation and Geoinformation
  • Mohammed Q Alkhatib
  • Research Article

Target Decomposition Feature-Guided Multi-Modal Domain Generalization Learning for Unsupervised PolSAR Image Classification

  • Jan 01, 2026
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Yice Cao +5
  • PDF
  • Research Article
  • Citations9

Generalized Zero-Shot Domain Adaptation for Unsupervised Cross-Domain PolSAR Image Classification

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Rong Gui +4
  • Research Article
  • Citations7

Self-Distillation-Based Polarimetric Image Classification with Noisy and Sparse Labels

  • Dec 15, 2023
  • Remote Sensing
  • Ningwei Wang +4
  • Research Article
  • Citations5

Stacked auto-encoder for classification of polarimetric SAR images based on scattering energy

  • Feb 15, 2019
  • International Journal of Remote Sensing
  • Ronghua Shang +4
  • Research Article
  • Citations8

Semisupervised Classification of PolSAR Images Using a Novel Memory Convolutional Neural Network

  • Jan 07, 2021
  • IEEE Geoscience and Remote Sensing Letters
  • Jun Guo +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.