• Home
  • Search
  • Target Decomposition Feature-Guided Multi-Modal Domain Generalization Learning for Unsupervised PolSAR Image Classification
  • https://doi.org/10.1109/jstars.2026.3670066Copy DOI Icon

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

  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Cross-domain (CD) models have been successfully applied to polarimetric synthetic aperture radar (PolSAR) image classification to alleviate the scarcity of labeled samples. However, these models often struggle to extract strongly generalizable domain-invariant features when encountering significant domain shifts. Furthermore, prevailing methods predominantly operate within the supervised domain adaptation paradigm, requiring access to target-domain data during training, which inherently limits their generalizability to entirely unseen target domains. Therefore, this paper proposes a target decomposition feature-guided multimodal domain generalization learning network (MMDGN), inspired by multimodality and domain generalization, for unsupervised classification of target-domain PolSAR images under the same frequency constraint. The core idea is to leverage the physical scattering mechanism consistency of the same frequency and categories to guide CD feature optimization, thereby enhancing the discriminative power and domain invariance of the features. The proposed MMDGN comprises three key modules: a multimodal feature extraction module that separately extracts image-modal and text-modal features, the latter derived from category-specific representative scattering components; a pattern memory-based space adjustment module that projects both modalities into a unified embedding space; and a dual-level semantic alignment module that integrates supervised contrastive learning with adversarial training to align multimodal features at both intra-class and inter-class levels. This promotes that the optimized image-modal features, guided by the text modality, exhibit intra-class compactness and inter-class separability. Experiments on six CD tasks constructed from three C-band PolSAR datasets demonstrate that MMDGN achieves state-of-the-art performance in unsupervised classification accuracy and CD generalization.

Similar Papers
  • 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
  • PDF
  • Research Article
  • Citations24

PolSAR Image Classification via Learned Superpixels and QCNN Integrating Color Features

  • Aug 06, 2019
  • Remote Sensing
  • Xinzheng Zhang +4
  • Research Article
  • Citations25

PolSAR Image Classification Using Hybrid Conditional Random Fields Model Based on Complex-Valued 3-D CNN

  • Jan 13, 2021
  • IEEE Transactions on Aerospace and Electronic Systems
  • Peng Zhang +6
  • Research Article
  • Citations6

Superpixel-Oriented Unsupervised Classification for Polarimetric SAR Images Based on Consensus Similarity Network Fusion

  • Jan 01, 2019
  • IEEE Access
  • Huanxin Zou +3
  • PDF
  • Research Article
  • Citations2

Two-step discriminant analysis based multi-view polarimetric SAR image classification with high confidence

  • Apr 08, 2022
  • Scientific Reports
  • Maryam Imani
  • 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
  • Research Article
  • Citations22

Variational Learning of Mixture Wishart Model for PolSAR Image Classification

  • Jan 01, 2019
  • IEEE Transactions on Geoscience and Remote Sensing
  • Qian Wu +3
  • Conference Article
  • Citations13

Polsar Image Crop Classification Based on Deep Residual Learning Network

  • Aug 01, 2018
  • Xin Mei +3
  • Research Article
  • Citations31

Copula-Based Joint Statistical Model for Polarimetric Features and Its Application in PolSAR Image Classification

  • Oct 01, 2017
  • IEEE Transactions on Geoscience and Remote Sensing
  • Hao Dong +4
  • Conference Article

Supervised classification of PolSAR images using adaptive sample censoring strategy

  • Aug 01, 2016
  • Tiancheng Luo +5
  • Research Article
  • Citations1

Unsupervised PolSAR Image Classification Based on Superpixel Pseudo-Labels and a Similarity-Matching Network

  • Nov 04, 2024
  • Remote Sensing
  • Lei Wang +4
  • PDF
  • Discussion
  • Citations10

Unsupervised Classification of Polarimetric SAR Image Based on Geodesic Distance and Non-Gaussian Distribution Feature.

  • Feb 12, 2021
  • Sensors
  • Junrong Qu +3
  • Research Article
  • Citations23

Unsupervised classification of polarimetric SAR image with dynamic clustering: An image processing approach

  • Jan 06, 2010
  • Advances in Engineering Software
  • Turker Ince
  • Research Article

Prototype Theory Based Feature Representation for PolSAR Images

  • Apr 28, 2016
  • Journal of Radars
  • Huang Xiaojing +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.