Polarimetric Synthetic Aperture Radar Image Classification Research Articles

A Deep Learning Classification Scheme for PolSAR Image Based on Polarimetric Features

Polarimetric features extracted from polarimetric synthetic aperture radar (PolSAR) images contain abundant back-scattering information about objects. Utilizing this information for PolSAR image classification can improve accuracy and enhance object monitoring. In this paper, a deep learning classification method based on polarimetric channel power features for PolSAR is proposed. The distinctive characteristic of this method is that the polarimetric features input into the deep learning network are the power values of polarimetric channels and contain complete polarimetric information. The other two input data schemes are designed to compare the proposed method. The neural network can utilize the extracted polarimetric features to classify images, and the classification accuracy analysis is employed to compare the strengths and weaknesses of the power-based scheme. It is worth mentioning that the polarized characteristics of the data input scheme mentioned in this article have been derived through rigorous mathematical deduction, and each polarimetric feature has a clear physical meaning. By testing different data input schemes on the Gaofen-3 (GF-3) PolSAR image, the experimental results show that the method proposed in this article outperforms existing methods and can improve the accuracy of classification to a certain extent, validating the effectiveness of this method in large-scale area classification.

Transfer-Aware Graph U-Net with Cross-Level Interactions for PolSAR Image Semantic Segmentation

Although graph convolutional networks have found application in polarimetric synthetic aperture radar (PolSAR) image classification tasks, the available approaches cannot operate on multiple graphs, which hinders their potential to generalize effective feature representations across different datasets. To overcome this limitation and achieve robust PolSAR image classification, this paper proposes a novel end-to-end cross-level interaction graph U-Net (CLIGUNet), where weighted max-relative spatial convolution is proposed to enable simultaneous learning of latent features from batch input. Moreover, it integrates weighted adjacency matrices, derived from the symmetric revised Wishart distance, to encode polarimetric similarity into weighted max-relative spatial graph convolution. Employing end-to-end trainable residual transformers with multi-head attention, our proposed cross-level interactions enable the decoder to fuse multi-scale graph feature representations, enhancing effective features from various scales through a deep supervision strategy. Additionally, multi-scale dynamic graphs are introduced to expand the receptive field, enabling trainable adjacency matrices with refined connectivity relationships and edge weights within each resolution. Experiments undertaken on real PolSAR datasets show the superiority of our CLIGUNet with respect to state-of-the-art networks in classification accuracy and robustness in handling unknown imagery with similar land covers.

Pol-SAR image classification using multifarious stratification stratagem in machine learning

Image classification using polarimetric synthetic aperture radar (Pol-SAR) is becoming more important in image processing for remote sensing applications. However, in the existing techniques, during the feature extraction process, there exist some limitations including laborious endeavour for Pol-SAR image classification, identifying intrinsic features for target recognition is difficult in feature selection, and pixel-level Pol-SAR image classification is difficult for obtaining more precise and coherent interpretation consequences. Hence to overcome these issues, a novel Multifarious Stratification Stratagem in machine learning is proposed to achieve pixel-level Pol-SAR classification. In this proposed model, a novel Scrumptious Integrant Wrenching method is used for efficient feature extraction. It is compatible with the orientation-sensitive of the Pol-SAR image which increases the variety of intra-layer features. To remove the difficulty in feature selection, a novel Episodicical Proximity Selection method is proposed in which a Split-level parallel feature selection strategy is used to select the best qualities from the extracted features. To tackle the difficulty in classification, an Elastic Net Classifier (ENC) is used that find the coefficient vector for the linear combination of the training sets. This efficiently classified the best features in the Pol-SAR images and improved the proposed system’s accuracy. As a result, the performance measures of the proposed system demonstrate that the accuracy is increased by 99.69%, precision is increased by 98.99%, recall is increased by 98.99%, sensitivity is increased by 98.99%, and F1-score is increased by 98.99% as a response.

A multi-view ensemble model based on semi-supervised feature learning for small sample classification of PolSAR images

ABSTRACT Classification with a few samples of training set has been a long-standing issue in the field of polarimetric synthetic aperture radar (PolSAR) image analysis and processing. In fact, one of the most important challenges of the PolSAR image classification task is the number of labelled samples. In essence, training network by utilizing just few numbers of training samples cannot be led to the reliable result since the neural network is so sensitive to the number of training samples. In addition, in the real PolSAR image classification task, the huge number of training samples is not accessible. On the other hand, classification performance using just small number of labelled samples is not an accurate result. So, in this paper, aiming at the small number of training samples of the PolSAR image classification task, a novel ensemble self-supervised feature-learning (ESSFL) model is designed. The designed ESSFL can automatically extract PolSAR features conducive to PolSAR image classification with a small number of training samples. In addition, it can significantly decrease the dependence of neural network algorithms on large labelled samples of training set. First, to utilize the spatial–polarimetric features of PolSAR data perfectly, the EfficientNet-B0 is presented and utilized as the main section of the deep learning (DL) model to extract DL features of PolSAR data. Then, using an optimization function that constrains the cross-correlation matrix of various distortions of each sample to the identity matrix, the designed deep learning model can obtain the effective features of homogeneous samples gathering together and heterogeneous samples separating from each other in a self-supervised manner. Moreover, two ensemble learning (EL) models, feature-level and view-level ensemble, are proposed to increase the feature extraction capability and classification result by jointly using spatial features at different scales and polarimetric information at different bands. Finally, the stack of the obtained features and the main polarimetric information of PolSAR data can be input into classifier for the classification of PolSAR data. In this paper we use two different classifiers, the first one is the Random Forest (RF) classifier and the second one is the Support Vector Machine (SVM) classifier. The advantages of SVM include that it can be used to avoid the difficulties of using linear functions in the high-dimensional feature space, and the optimization problem is transformed into dual convex quadratic programs that are so usable for an actual image classification task. In addition, among all the available classification methods, random forests provide one of the highest accuracies. The random forest technique can also handle big data with numerous variables running into thousands. In fact, it can automatically balance data sets when a class is more infrequent than other classes in the data that is so important for a real PolSAR image classification task. Experimental results on three well-known PolSAR data sets illustrate that the designed ESSFL can extract more discriminant features using the designed deep learning model. In the end, the experiments prove that the designed ESSFL has a significant classification performance compared with different deep learning models in the case of small number of training samples, and also it can achieve a better result in the case of large number of training samples by comparison with the most of the deep learning models.

Global Polarimetric Synthetic Aperture Radar Image Segmentation with Data Augmentation and Hybrid Architecture Model

Machine learning and deep neural networks have shown satisfactory performance in the supervised classification of Polarimetric Synthetic Aperture Radar (PolSAR) images. However, the PolSAR image classification task still faces some challenges. First, the current form of model input used for this task inevitably involves tedious preprocessing. In addition, issues such as insufficient labels and the design of the model also affect classification performance. To address these issues, this study proposes an augmentation method to better utilize the labeled data and improve the input format of the model, and an end-to-end PolSAR image global classification is implemented on our proposed hybrid network, PolSARMixer. Experimental results demonstrate that, compared to existing methods, our proposed method reduces the steps for the classification of PolSAR images, thus eliminating repetitive data preprocessing procedures and significantly improving classification performance.

PolSAR Image Classification Based on Multi-Modal Contrastive Fully Convolutional Network

Deep neural networks have achieved remarkable results in the field of polarimetric synthetic aperture radar (PolSAR) image classification. However, PolSAR is affected by speckle imaging, resulting in PolSAR images usually containing a large amount of speckle noise, which usually leads to the poor spatial consistency of classification results and insufficient classification accuracy. Semantic segmentation methods based on deep learning can realize the task of image segmentation and classification at the same time, producing fine-grained and smooth classification maps. However, these approaches require enormous labeled data sets, which are laborious and time-consuming. Due to these issues, a new multi-modal contrastive fully convolutional network, named MCFCN, is proposed for PolSAR image classification in this paper, which combines multi-modal features of the same pixel as inputs to the model based on a fully convolutional network and accomplishes the classification task using only a small amount of labeled data through contrastive learning. In addition, to describe the PolSAR terrain targets more comprehensively and enhance the robustness of the classifier, a pixel overlapping classification strategy is proposed, which can not only improve the classification accuracy effectively but also enhance the stability of the method. The experiments demonstrate that compared with existing classification methods, the classification results of the proposed method for three real PolSAR datasets have higher classification accuracy.

Machine learning classification based on k-Nearest Neighbors for PolSAR data.

In this work, we focus on obtaining insights of the performances of some well-known machine learning image classification techniques (k-NN, Support Vector Machine, randomized decision tree and one based on stochastic distances) for PolSAR (Polarimetric Synthetic Aperture Radar) imagery. We test the classifiers methods on a set of actual PolSAR data and provide some conclusions. The aim of this work is to show that suitable adapted standard machine learning methods offer excellent performances vs.computational complexity trade-off for PolSAR image classification. In this work, we evaluate well-known machine learning techniques for PolSAR (Polarimetric Synthetic Aperture Radar) image classification, including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), randomized decision tree, and a method based on the Kullback-Leibler stochastic distance. Our experiments with real PolSAR data show that standard machine learning methods, when adapted appropriately, offer a favourable trade-off between performance and computational complexity. The KNN and SVM perform poorly on these data, likely due to their failure to account for the inherent speckle presence and properties of the studied reliefs. Overall, our findings highlight the potential of the Kullback-Leibler stochastic distance method for PolSAR image classification.

PolSAR image classification based on TCN deep learning: a case study of greater Cairo

ABSTRACT Environmental applications play a significant role in the ongoing research area of Polarimetric Synthetic Aperture Radar (PolSAR) image classification. In this paper, a new model is proposed for classifying PolSAR images and applied to a part of the Greater Cairo area in the Nile basin, South of Delta, Egypt. First, the proposed model performs data pre-processing by extracting the coherency and covariance elements noted as [T] and [C] matrices, respectively. Second, temporal convolutional networks (TCN) deep learning is used to extract the features from coherency and covariance elements and then train the model. Third, the SoftMax classifier is used to classify the PolSAR image. Finally, the proposed model is tested with evaluation metrics. The obtained results show that the proposed model can achieve high classification performances.

Polarimetric SAR Image Classification Based on Hierarchical Scattering-Spatial Interaction Transformer

Polarimetric SAR Image Classification Based on Hierarchical Scattering-Spatial Interaction Transformer

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

Polarimetric synthetic aperture radar (PolSAR) image classification, a field crucial in remote sensing, faces significant challenges due to the intricate expertise required for accurate annotation, leading to susceptibility to labeling inaccuracies. Compounding this challenge are the constraints posed by limited labeled samples and the perennial issue of class imbalance inherent in PolSAR image classification. Our research objectives are to address these challenges by developing a novel label correction mechanism, implementing self-distillation-based contrastive learning, and introducing a sample rebalancing loss function. To address the quandary of noisy labels, we proffer a novel label correction mechanism that capitalizes on inherent sample similarities to rectify erroneously labeled instances. In parallel, to mitigate the limitation of sparsely labeled data, this study delves into self-distillation-based contrastive learning, harnessing sample affinities for nuanced feature extraction. Moreover, we introduce a sample rebalancing loss function that adjusts class weights and augments data for small classes. Through extensive experiments on four benchmark PolSAR images, our approach demonstrates its effectiveness in addressing label inaccuracies, limited samples, and class imbalance. Through extensive experiments on four benchmark PolSAR images, our research substantiates the robustness of our proposed methodology, particularly in rectifying label discrepancies in contexts marked by sample paucity and imbalance. The empirical findings illuminate the superior efficacy of our approach, positioning it at the forefront of state-of-the-art PolSAR classification techniques.

Polarimetric Synthetic Aperture Radar Image Classification Based on Double-Channel Convolution Network and Edge-Preserving Markov Random Field

Deep learning methods have gained significant popularity in the field of polarimetric synthetic aperture radar (PolSAR) image classification. These methods aim to extract high-level semantic features from the original PolSAR data to learn the polarimetric information. However, using only original data, these methods cannot learn multiple scattering features and complex structures for extremely heterogeneous terrain objects. In addition, deep learning methods always cause edge confusion due to the high-level features. To overcome these limitations, we propose a novel approach that combines a new double-channel convolutional neural network (CNN) with an edge-preserving Markov random field (MRF) model for PolSAR image classification, abbreviated to “DCCNN-MRF”. Firstly, a double-channel convolution network (DCCNN) is developed to combine complex matrix data and multiple scattering features. The DCCNN consists of two subnetworks: a Wishart-based complex matrix network and a multi-feature network. The Wishart-based complex matrix network focuses on learning the statistical characteristics and channel correlation, and the multi-feature network is designed to learn high-level semantic features well. Then, a unified network framework is designed to fuse two kinds of weighted features in order to enhance advantageous features and reduce redundant ones. Finally, an edge-preserving MRF model is integrated with the DCCNN network. In the MRF model, a sketch map-based edge energy function is designed by defining an adaptive weighted neighborhood for edge pixels. Experiments were conducted on four real PolSAR datasets with different sensors and bands. The experimental results demonstrate the effectiveness of the proposed DCCNN-MRF method.

A novel self‐supervised ensemble learning framework for land use and land cover classification of polarimetric synthetic aperture radar images

AbstractClassification with a few samples of training set has been a longstanding issue in the field of polarimetric synthetic aperture radar (PolSAR) image analysis and processing. Aiming at the small number of training samples of the PolSAR image classification task, a novel Self‐Supervised Ensemble Learning Framework (SSELF) is designed. The designed SSELF can automatically extract PolSAR features conducive to PolSAR image classification with a small number of training samples. In addition, it can significantly decrease the dependence of neural network algorithms on large labelled samples of training set. First, utilise the spatial–polarimetric features of PolSAR data perfectly, the EfficientNet‐B0 is presented and utilised as the main section of the Deep Learning (DL) model to extract DL features of PolSAR data. Then, using an optimisation function that constrains the cross‐correlation matrix of various distortions of each sample to the identity matrix, the designed DL model can obtain the effective features of homogeneous samples gathering and heterogeneous samples separating from each other in a self‐supervised manner. Moreover, following the great success of curriculum learning in the area of machine learning, a novel deep curriculum‐learning model is proposed, entitled Deep Curriculum Learning (DCL), to train the DL network in our self‐supervised model. The proposed DCL utilises the entropy‐alpha target decomposition to estimate the degree of complexity of each PolSAR image patch before applying it to the EfficientNet‐B0. Also, an accumulative mini‐batch pacing function is used to introduce more difficult patches to EfficientNet‐B0 in the training process of the designed self‐supervised model. Furthermore, two EL models, feature‐level and view‐level ensemble, are proposed to increase the feature extraction capability and classification result of PolSAR data by jointly using spatial features at different scales and polarimetric information at different bands. In fact, in the proposed feature‐level ensemble strategy, to improve the classification result, the extracted features of the different scales are used as the input of the designed feature fusion algorithm. Therefore, the extracted features are mapped to the new space with lower dimension. In general, in the proposed view‐level ensemble strategy, first, the Mutual Information (MI) between each feature and the other features calculates, and then based‐on the calculated MI, different group of features are selected as various views. Next, the final classification result of the PolSAR image classification is obtained by using the designed majority vote of the result in each view. It should be noted that unlike existing traditional methods, both amplitude and phase information of SAR images to devolve the training process of the proposed model are used. In addition, all of the parameters of the proposed network are developed to a complex domain. In addition, a complex backpropagation algorithm by using the gradient‐based model is used for training the network. Finally, experimental results on three well‐known PolSAR data sets illustrate that the designed SSELF can extract more discriminant features using the designed DL model and can achieve better classification results than the other six novel DL models in terms of small training samples and adequate labelled samples.

A New Architecture of a Complex-Valued Convolutional Neural Network for PolSAR Image Classification

Polarimetric synthetic aperture radar (PolSAR) image classification has been an important area of research due to its wide range of applications. Traditional machine learning methods were insufficient in achieving satisfactory results before the advent of deep learning. Results have significantly improved with the widespread use of deep learning in PolSAR image classification. However, the challenge of reconciling the complex-valued inputs of PolSAR images with the real-valued models of deep learning remains unsolved. Current complex-valued deep learning models treat complex numbers as two distinct real numbers, providing limited assistance in PolSAR image classification results. This paper proposes a novel, complex-valued deep learning approach for PolSAR image classification to address this issue. The approach includes amplitude-based max pooling, complex-valued nonlinear activation, and a cross-entropy loss function based on complex-valued probability. Amplitude-based max pooling reduces computational effort while preserving the most valuable complex-valued features. Complex-valued nonlinear activation maps feature into a high-dimensional complex-domain space, producing the most discriminative features. The complex-valued cross-entropy loss function computes the classification loss using the complex-valued model output and dataset labels, resulting in more accurate and robust classification results. The proposed method was applied to a shallow CNN, deep CNN, FCN, and SegNet, and its effectiveness was verified on three public datasets. The results showed that the method achieved optimal classification results on any model and dataset.

PolSAR Image Classification by Introducing POA and HA Variances

A polarimetric synthetic aperture radar (PolSAR) has great potential in ground target classification. However, current methods experience difficulties in separating forests and buildings, especially oriented buildings. To address this issue, inspired by the three-component decomposition method, multiple new scattering models were proposed to describe the difference between forest scattering and building scattering. However, this problem cannot effectively be solved with scattering power alone since HV polarization records significant scattering powers from building areas that are similar to vegetation. Therefore, in this study, two new parameters, the polarization orientation angle (POA) variance and helix angle (HA) variance, were defined to describe the distributions of buildings and forests. By combining scattering power with POA and HA variances, the random forest algorithm was used to conduct the land cover classification, focusing on distinguishing between forests and oriented buildings. Finally, the C- and L-band polarimetric SAR data acquired by the GF-3, ALOS1 PALSAR, and SAOCOM systems were selected to test the proposed method. The results indicate that it is feasible to improve PolSAR classification accuracy by introducing polarimetric parameters. Quantitatively, the classification accuracies increased by 23.78%, 10.80%, and 12.97% for the ALOS1 PALSAR, GF-3, and SAOCOM data, respectively.

Object-oriented polarimetric SAR image classification via the combination of a pixel-based classifier and a region growing technique

ABSTRACT Land-cover type interpretation by the use of remote sensing image classification techniques is always a hot topic. In this paper, an object-oriented method is presented for fully polarimetric synthetic aperture radar (SAR) image classification. Differing from most of the traditional object-oriented classification algorithms, the proposed method employs an innovative classification strategy that combines a pixel-based classifier and a region growing technique. Firstly, taking each individual pixel as a seed pixel, the homogeneous areas are extracted by a region growing technique. Then, using the information of the pixel-based classification result, the pixels located in each homogeneous area are all assigned to a certain class. Finally, the majority voting strategy is deployed to determine the final class label of each pixel. The experiments conducted on two fully polarimetric SAR images reveal that the proposed classification scheme can obtain pleasing classification accuracy and can provide the classification maps with more homogeneous regions than pixel-based classification.

A polarimetric projection-based scattering characteristics extraction tool and its application to PolSAR image classification

It is necessary to adequately extract scattering characteristics from polarimetric synthetic aperture radar (PolSAR) data for land-cover classification. Current interpretation technologies, such as target decompositions, polarimetric signatures, and polarimetric coherence patterns, have been widely used to explore polarization information. However, because limited scattering models are used to characterize all ground targets, these methods are occasionally limited in the interpretation of PolSAR data. This may reduce the accuracy of the land-cover classification. In this study, we attempted to extract the scattering characteristics through another novel method. We understand the PolSAR image interpretation as the projection of the scattering model on the measured matrix. Current methods project only a limited series of scattering models onto a measured matrix. To complement current methods of PolSAR image interpretation, we propose a polarimetric projection-based scattering characteristics extraction (PPSCE) method. It projects scattering models consisting of four changing independent polarization parameters onto the measured matrix. These scattering models, associated with the geometric and physical properties of the ground targets, correspond to the entire polarization space. The PPSCE method, meanwhile, extracts polarization information sufficiently. L-band UAVSAR, C-band Radarsat-2, and P-band AIRSAR images of classical experimental areas are used to validate the PPSCE method. The results show that the proposed PPSCE method can present polarization information that is difficult to investigate by the existing methods. In addition, the scattering features derived using the PPSCE method are superior for land-cover classification. Compared to the classification results based on the coherency matrix and Wishart classifier, the proposed method improves the overall classification accuracy by 23.56% for UAVSAR data. Compared to target decompositions and polarization signatures, the overall classification accuracy of the proposed method is increased by 29.32% (RF) and 22.63% (SVM) for UAVSAR data, 7.96% (RF) and 4.36% (RF) for Radarsat-2 and AIRSAR datasets, respectively. Furthermore, the proposed method has significant potential for soil moisture inversion. https://rgdoi.net/10.13140/RG.2.2.14091.26409.

MCPT: Mixed Convolutional Parallel Transformer for Polarimetric SAR Image Classification

Vision transformers (ViT) have the characteristics of massive training data and complex model, which cannot be directly applied to polarimetric synthetic aperture radar (PolSAR) image classification tasks. Therefore, a mixed convolutional parallel transformer (MCPT) model based on ViT is proposed for fast PolSAR image classification. First of all, a mixed depthwise convolution tokenization is introduced. It replaces the learnable linear projection in the original ViT to obtain patch embeddings. The process of tokenization can reduce computational and parameter complexity and extract features of different receptive fields as input to the encoder. Furthermore, combining the idea of shallow networks with lower latency and easier optimization, a parallel encoder is implemented by pairing the same modules and recombining to form parallel blocks, which can decrease the network depth and computing power requirement. In addition, the original class embedding and position embedding are removed during tokenization, and a global average pooling layer is added after the encoder for category feature extraction. Finally, the experimental results on AIRSAR Flevoland and RADARSAT-2 San Francisco datasets show that the proposed method achieves a significant improvement in training and prediction speed. Meanwhile, the overall accuracy achieved was 97.9% and 96.77%, respectively.

PolSAR Image Classification Based on Relation Network with SWANet

Deep learning and convolutional neural networks (CNN) have been widely applied in polarimetric synthetic aperture radar (PolSAR) image classification, and satisfactory results have been obtained. However, there is one crucial issue that still has not been solved. These methods require abundant labeled samples and obtaining the labeled samples of PolSAR images is usually time-consuming and labor-intensive. To obtain better classification results with fewer labeled samples, a new attention-based 3D residual relation network (3D-ARRN) is proposed for PolSAR image. Firstly, a multilayer CNN with residual structure is used to extract depth polarimetric features. Secondly, to extract more important feature information and improve the classification results, a spatial weighted attention network (SWANet) is introduced to concentrate the feature information, which is more favorable for a classification task. Then, the features of training and test samples are integrated and CNN is utilized to compute the score of similarity between training and test samples. Finally, the similarity score is used to determine the category of test samples. Studies on four different PolSAR datasets illustrate that the proposed 3D-ARRN model can achieve higher classification results than other comparison methods with few labeled data.

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

Highly accurate supervised deep learning-based classifiers for polarimetric synthetic aperture radar (PolSAR) images require large amounts of data with manual annotations. Unfortunately, the complex echo imaging mechanism results in a high labeling cost for PolSAR images. Extracting and transferring knowledge to utilize the existing labeled data to the fullest extent is a viable approach in such circumstances. To this end, we are introducing unsupervised deep adversarial domain adaptation (ADA) into PolSAR image classification for the first time. In contrast to the standard learning paradigm, in this study, the deep learning model is trained on labeled data from a source domain and unlabeled data from a related but distinct target domain. The purpose of this is to extract domain-invariant features and generalize them to the target domain. Although the feature transferability of ADA methods can be ensured through adversarial training to align the feature distributions of source and target domains, improving feature discriminability remains a crucial issue. In this paper, we propose a novel polarimetric scattering characteristics-guided adversarial network (PSCAN) for unsupervised PolSAR image classification. Compared with classical ADA methods, we designed an auxiliary task for PSCAN based on the polarimetric scattering characteristics-guided pseudo-label construction. This approach utilizes the rich information contained in the PolSAR data itself, without the need for expensive manual annotations or complex automatic labeling mechanisms. During the training of PSCAN, the auxiliary task receives category semantic information from pseudo-labels and helps promote the discriminability of the learned domain-invariant features, thereby enabling the model to have a better target prediction function. The effectiveness of the proposed method was demonstrated using data captured with different PolSAR systems in the San Francisco and Qingdao areas. Experimental results show that the proposed method can obtain satisfactory unsupervised classification results.

Feature fusion method based on local binary graph for PolSAR image classification

AbstractThe goal of this paper is to propose a method to achieve a higher classification rate in Polarimetric Synthetic Aperture Radar (PolSAR) image classification. In our work, PolSAR features are extracted from Convolutional Neural Networks (CNNs) and also Graph Convolutional Networks (GCNs). Due to the construction of the adjacency matrix on all the data, traditional GCNs usually suffer from a substantial computational cost, particularly in large‐scale remote sensing (RS) problems. To this end, first of all, we propose a new mini‐batch GCN (called Mini‐GCN), which allows to train large‐scale GCNs in a mini‐batch fashion. More significantly, our designed mini‐GCN is capable of inferring out‐of‐sample data without re‐training networks and improving classification performance. Furthermore, as CNNs and GCNs can extract different types of PolSAR features, an intuitive solution to break the performance bottleneck of a single model is to fuse them. Since mini‐GCNs can perform batch‐wise network training (enabling the combination of CNNs and GCNs), we can use the feature fusion strategy. Therefore, in this paper, a local graph‐based fusion method is proposed to couple dimension reduction and feature fusion of the information extracted from the designed CNN and Mini‐GCN. Experimental results on real PolSAR data are very encouraging. Compared to the methods using only single feature and stacking all the features together, the proposed feature fusion method improves the overall classification accuracy on the real PolSAR data sets for more than 5%. Moreover, the experiments conducted on PolSAR datasets, demonstrate the advantages of the used mini‐GCNs over the traditional GCNs and the superiority of the proposed feature fusion method with regards to the single CNN or GCN models.