# Dual-Branch Fusion of Convolutional Neural Network and Graph Convolutional Network for PolSAR Image Classification

^{1}

^{2}

^{3}

^{4}

^{*}

## Abstract

**:**

## 1. Introduction

- (1)
- Considering different PolSAR image characteristics, we attempt to derive network-specific features by dividing them into spatial and polarimetric categories. Hence, Pauli RGB and Yamaguchi decomposition of the PolSAR image present spatial feature channels, and six roll-invariant and hidden polarimetric features are polarimetric features channels.
- (2)
- The novel method of supervised batchwise version of GCN, known as miniGCN, is investigated as a classifier for PolSAR image classification.
- (3)
- Dual-branch fusion of miniGCN and CNN is proposed as a PolSAR classifier. Thus, each miniGCN and CNN is fed by the features with specific characteristics corresponding to its structure. Particularly, miniGCN and CNN extract spatial and polarimetric features, respectively. Subsequently, their integrated features are followed by two FC layers to determine PolSAR image classes.

## 2. Theory and Basics of CNN and miniGCN

#### 2.1. CNNs Basics and Overview

#### 2.2. Graph and miniGCN

_{i}and x

_{j}are the feature vector corresponding to vertices v

_{i}and v

_{j}and σ is the control parameter of the RBF. Accordingly, the normalized graph Laplacian matrix L is represented using diagonal matrix D as follows [40]:

_{θ}(Λ) is a filter in the Fourier domain that represents the function of eigenvalues (Λ) of L considering the variable θ. The Kth order truncated expansion of Chebyshev polynomials is used to alleviate the computational cost of convolutional on a graph [41].

_{k}donates Chebyshev polynomials. Normalized $\tilde{L}$ is scaled as $\tilde{L}=2L/{\lambda}_{max}-I$. Eventually, Equation (6) can be simplified by considering K = 1 and λ

_{max}= 2:

^{l}, b

^{l}, and h() are weight matrix, bias matrix, and activation function. The output of lth and (l + 1)th layers are also indicated by H

^{l}and H

^{l+1}.

_{s}):

## 3. The Proposed Method

#### 3.1. PolSAR Feature Extraction

_{HV}= S

_{VH}) in case of satisfying the reciprocity theorem. It can be represented in a way to highlight specific scattering mechanisms:

_{2}|

^{2}(S

_{HH}− S

_{VV}), |a

_{3}|

^{2}(2S

_{HV}), and |a

_{1}|

^{2}(S

_{HH}+ S

_{VV}). This pseudo-colored image is more human-desirable and in close harmony with natural colors [42], making it easier to consider spatial characteristics such as other colored images. The Coherency matrix T

_{3}can be obtained as follows:

_{i}is the ith sample of Pauli scattering vector (k), and L indicates the number of looks.

_{3}into the four scattering powers of surface (P

_{s}), double-bounce (P

_{d}), volume (P

_{v}), and helix scattering (P

_{h}) [39]. This decomposition is valuable for characterizing urban man-made targets, owing to the helix scattering component that emerges in heterogenous areas [9].

_{HH}|

^{2}+ 2|S

_{HV}|

^{2}+ |S

_{VV}|

^{2}

_{1}, λ

_{2}, and λ

_{3}are eigenvalues and U

_{3}comprises eigenvectors of the coherency matrix. Accordingly, Cloude–Pottier decomposition components [43], including entropy (H), mean alpha angle ($\overline{\alpha}$), and anisotropy (A) are derived.

_{null}. The null angles of θ

_{null}_Re[T

_{12}] and θ

_{null}_Im[T

_{12}] are highly sensitive to various land covers, which offers a lot of potential for PolSAR classification. These two null angles are presented as follows:

_{null}_Re[T

_{12}], and θ

_{null}_Im[T

_{12}] are considered for representing and modeling polarimetric characteristics of PolSAR images.

#### 3.2. Dual-Branch FuNet Architecture

## 4. Experiments

#### 4.1. Data Description

#### 4.2. Experimental Design

#### 4.3. Parameter Setting, Adjacency Matrix

#### 4.4. Effectiveness Evaluation

#### 4.5. Experiments on AIRSAR Datasets

#### 4.6. Performance Analyses with Different Training Sampling Rates

#### 4.7. Comparison with Other Studies

## 5. Conclusions

## Author Contributions

## Funding

## Data Availability Statement

## Conflicts of Interest

## References

- Ren, B.; Hou, B.; Zhao, J.; Jiao, L. Sparse subspace clustering-based feature extraction for PolSAR imagery classification. Remote Sens.
**2018**, 10, 391. [Google Scholar] [CrossRef][Green Version] - Zhang, Q.; Wei, X.; Xiang, D.; Sun, M. Supervised PolSAR Image Classification with Multiple Features and Locally Linear Embedding. Sensors
**2018**, 18, 3054. [Google Scholar] [CrossRef][Green Version] - Zhong, N.; Yang, W.; Cherian, A.; Yang, X.; Xia, G.-S.; Liao, M. Unsupervised classification of polarimetric SAR images via Riemannian sparse coding. IEEE Trans. Geosci. Remote Sens.
**2017**, 55, 5381–5390. [Google Scholar] [CrossRef] - Doulgeris, A.P.; Anfinsen, S.N.; Eltoft, T. Automated non-Gaussian clustering of polarimetric synthetic aperture radar images. IEEE Trans. Geosci. Remote Sens.
**2011**, 49, 3665–3676. [Google Scholar] [CrossRef] - Yin, J.; Liu, X.; Yang, J.; Chu, C.-Y.; Chang, Y.-L. PolSAR image classification based on statistical distribution and MRF. Remote Sens.
**2020**, 12, 1027. [Google Scholar] [CrossRef][Green Version] - Jafari, M.; Maghsoudi, Y.; Zoej, M.J.V. A new method for land cover characterization and classification of polarimetric SAR data using polarimetric signatures. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
**2015**, 8, 3595–3607. [Google Scholar] [CrossRef] - Freeman, A.; Durden, S.L. A three-component scattering model for polarimetric SAR data. IEEE Trans. Geosci. Remote Sens.
**1998**, 36, 963–973. [Google Scholar] [CrossRef][Green Version] - Krogager, E. New decomposition of the radar target scattering matrix. Electron. Lett.
**1990**, 26, 1525–1527. [Google Scholar] [CrossRef] - Yamaguchi, Y.; Moriyama, T.; Ishido, M.; Yamada, H. Four-component scattering model for polarimetric SAR image decomposition. IEEE Trans. Geosci. Remote Sens.
**2005**, 43, 1699–1706. [Google Scholar] [CrossRef] - Fan, J.; Wang, X.; Wang, X.; Zhao, J.; Liu, X. Incremental wishart broad learning system for fast PolSAR image classification. IEEE Geosci. Remote Sens. Lett.
**2019**, 16, 1854–1858. [Google Scholar] [CrossRef] - Lee, J.-S.; Grunes, M.R.; Kwok, R. Classification of multi-look polarimetric SAR imagery based on complex Wishart distribution. Int. J. Remote Sens.
**1994**, 15, 2299–2311. [Google Scholar] [CrossRef] - Chaudhari, N.; Mitra, S.K.; Mandal, S.; Chirakkal, S.; Putrevu, D.; Misra, A. Edge-Preserving classification of polarimetric SAR images using Wishart distribution and conditional random field. Int. J. Remote Sens.
**2022**, 43, 2134–2155. [Google Scholar] [CrossRef] - Khosravi, I.; Safari, A.; Homayouni, S.; McNairn, H. Enhanced decision tree ensembles for land-cover mapping from fully polarimetric SAR data. Int. J. Remote Sens.
**2017**, 38, 7138–7160. [Google Scholar] [CrossRef] - Qi, Z.; Yeh, A.G.-O.; Li, X.; Lin, Z. A novel algorithm for land use and land cover classification using RADARSAT-2 polarimetric SAR data. Remote Sens. Environ.
**2012**, 118, 21–39. [Google Scholar] [CrossRef] - Zhang, L.; Zou, B.; Zhang, J.; Zhang, Y. Classification of polarimetric SAR image based on support vector machine using multiple-component scattering model and texture features. EURASIP J. Adv. Signal Process.
**2009**, 2010, 1–9. [Google Scholar] [CrossRef][Green Version] - Tao, C.; Chen, S.; Li, Y.; Xiao, S. PolSAR land cover classification based on roll-invariant and selected hidden polarimetric features in the rotation domain. Remote Sens.
**2017**, 9, 660. [Google Scholar] [CrossRef][Green Version] - Zhou, Y.; Wang, H.; Xu, F.; Jin, Y.-Q. Polarimetric SAR image classification using deep convolutional neural networks. IEEE Geosci. Remote Sens. Lett.
**2016**, 13, 1935–1939. [Google Scholar] [CrossRef] - Zhang, L.; Ma, W.; Zhang, D. Stacked sparse autoencoder in PolSAR data classification using local spatial information. IEEE Geosci. Remote Sens. Lett.
**2016**, 13, 1359–1363. [Google Scholar] [CrossRef] - Chen, Y.; Jiao, L.; Li, Y.; Zhao, J. Multilayer projective dictionary pair learning and sparse autoencoder for PolSAR image classification. IEEE Trans. Geosci. Remote Sens.
**2017**, 55, 6683–6694. [Google Scholar] [CrossRef] - Lv, Q.; Dou, Y.; Niu, X.; Xu, J.; Li, B. Classification of Land Cover Based on Deep Belief Networks Using Polarimetric RADARSAT-2 Data. In Proceedings of the 2014 IEEE Geoscience and Remote Sensing Symposium, Quebec City, QC, Canada, 13–18 July 2014; pp. 4679–4682. [Google Scholar]
- Jamali, A.; Mahdianpari, M.; Mohammadimanesh, F.; Bhattacharya, A.; Homayouni, S. PolSAR image classification based on deep convolutional neural networks using wavelet transformation. IEEE Geosci. Remote Sens. Lett.
**2022**, 19, 4510105. [Google Scholar] [CrossRef] - Xie, W.; Jiao, L.; Hua, W. Complex-Valued Multi-Scale Fully Convolutional Network with Stacked-Dilated Convolution for PolSAR Image Classification. Remote Sens.
**2022**, 14, 3737. [Google Scholar] [CrossRef] - Hua, W.; Xie, W.; Jin, X. Three-Channel Convolutional Neural Network for Polarimetric SAR Images Classification. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
**2020**, 13, 4895–4907. [Google Scholar] [CrossRef] - Wang, H.; Xing, C.; Yin, J.; Yang, J. Land Cover Classification for Polarimetric SAR Images Based on Vision Transformer. Remote Sens.
**2022**, 14, 4656. [Google Scholar] [CrossRef] - Chen, S.-W.; Tao, C.-S. PolSAR image classification using polarimetric-feature-driven deep convolutional neural network. IEEE Geosci. Remote Sens. Lett.
**2018**, 15, 627–631. [Google Scholar] [CrossRef] - Zhang, Z.; Wang, H.; Xu, F.; Jin, Y.-Q. Complex-valued convolutional neural network and its application in polarimetric SAR image classification. IEEE Trans. Geosci. Remote Sens.
**2017**, 55, 7177–7188. [Google Scholar] [CrossRef] - Gao, F.; Huang, T.; Wang, J.; Sun, J.; Hussain, A.; Yang, E. Dual-branch deep convolution neural network for polarimetric SAR image classification. Appl. Sci.
**2017**, 7, 447. [Google Scholar] [CrossRef][Green Version] - Wang, Y.; Cheng, J.; Zhou, Y.; Zhang, F.; Yin, Q. A Multichannel Fusion Convolutional Neural Network Based on Scattering Mechanism for PolSAR Image Classification. IEEE Geosci. Remote Sens. Lett.
**2021**, 19, 4007805. [Google Scholar] [CrossRef] - Shang, R.; Wang, J.; Jiao, L.; Yang, X.; Li, Y. Spatial feature-based convolutional neural network for PolSAR image classification. Appl. Soft Comput.
**2022**, 123, 108922. [Google Scholar] [CrossRef] - Kipf, T.N.; Welling, M. Semi-supervised classification with graph convolutional networks. arXiv
**2016**, arXiv:1609.02907. [Google Scholar] - Qin, A.; Shang, Z.; Tian, J.; Wang, Y.; Zhang, T.; Tang, Y.Y. Spectral–spatial graph convolutional networks for semisupervised hyperspectral image classification. IEEE Geosci. Remote Sens. Lett.
**2018**, 16, 241–245. [Google Scholar] [CrossRef] - Wan, S.; Gong, C.; Zhong, P.; Pan, S.; Li, G.; Yang, J. Hyperspectral image classification with context-aware dynamic graph convolutional network. IEEE Trans. Geosci. Remote Sens.
**2020**, 59, 597–612. [Google Scholar] [CrossRef] - Ding, Y.; Zhang, Z.; Zhao, X.; Hong, D.; Li, W.; Cai, W.; Zhan, Y. AF2GNN: Graph convolution with adaptive filters and aggregator fusion for hyperspectral image classification. Inf. Sci.
**2022**, 602, 201–219. [Google Scholar] [CrossRef] - Yao, D.; Zhi-li, Z.; Xiao-feng, Z.; Wei, C.; Fang, H.; Yao-ming, C.; Cai, W.-W. Deep hybrid: Multi-graph neural network collaboration for hyperspectral image classification. Def. Technol. 2022, in press. [CrossRef]
- He, X.; Chen, Y.; Ghamisi, P. Dual Graph Convolutional Network for Hyperspectral Image Classification with Limited Training Samples. IEEE Trans. Geosci. Remote Sens.
**2021**, 60, 5502418. [Google Scholar] [CrossRef] - Hong, D.; Gao, L.; Yao, J.; Zhang, B.; Plaza, A.; Chanussot, J. Graph convolutional networks for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens.
**2020**, 59, 5966–5978. [Google Scholar] [CrossRef] - Cai, W.; Wei, Z. Remote sensing image classification based on a cross-attention mechanism and graph convolution. IEEE Geosci. Remote Sens. Lett.
**2020**, 19, 8002005. [Google Scholar] [CrossRef] - Du, X.; Zheng, X.; Lu, X.; Doudkin, A.A. Multisource remote sensing data classification with graph fusion network. IEEE Trans. Geosci. Remote Sens.
**2021**, 59, 10062–10072. [Google Scholar] [CrossRef] - Yamaguchi, Y.; Sato, A.; Boerner, W.-M.; Sato, R.; Yamada, H. Four-component scattering power decomposition with rotation of coherency matrix. IEEE Trans. Geosci. Remote Sens.
**2011**, 49, 2251–2258. [Google Scholar] [CrossRef] - Hong, D.; Yokoya, N.; Ge, N.; Chanussot, J.; Zhu, X.X. Learnable manifold alignment (LeMA): A semi-supervised cross-modality learning framework for land cover and land use classification. ISPRS J. Photogramm. Remote Sens.
**2019**, 147, 193–205. [Google Scholar] [CrossRef] - Hammond, D.K.; Vandergheynst, P.; Gribonval, R. Wavelets on graphs via spectral graph theory. Appl. Comput. Harmon. Anal.
**2011**, 30, 129–150. [Google Scholar] [CrossRef][Green Version] - Uhlmann, S.; Kiranyaz, S. Integrating color features in polarimetric SAR image classification. IEEE Trans. Geosci. Remote Sens.
**2013**, 52, 2197–2216. [Google Scholar] [CrossRef] - Cloude, S.R.; Pottier, E. An entropy based classification scheme for land applications of polarimetric SAR. IEEE Trans. Geosci. Remote Sens.
**1997**, 35, 68–78. [Google Scholar] [CrossRef] - Chen, S.-W.; Wang, X.-S.; Sato, M. Uniform polarimetric matrix rotation theory and its applications. IEEE Trans. Geosci. Remote Sens.
**2013**, 52, 4756–4770. [Google Scholar] [CrossRef] - Liu, X.; Jiao, L.; Liu, F. PolSF: PolSAR Image Dataset on San Francisco. arXiv
**2019**, arXiv:1912.07259. [Google Scholar] - Lee, J.-S.; Grunes, M.R.; De Grandi, G. Polarimetric SAR speckle filtering and its implication for classification. IEEE Trans. Geosci. Remote Sens.
**1999**, 37, 2363–2373. [Google Scholar] - Ren, S.; Zhou, F. Semi-Supervised Classification for PolSAR Data with Multi-Scale Evolving Weighted Graph Convolutional Network. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
**2021**, 14, 2911–2927. [Google Scholar] [CrossRef]

**Figure 3.**Batchwise structure of miniGCN. Three minibatches are considered with the random node sampler size of M = 4, compared to full graph with N = 12 nodes.

**Figure 4.**The framework of the proposed dual-branch FuNet, including three main steps: polarimetric and spatial feature extraction, miniGCN and CNN layers, and fusion layers leading to a classified PolSAR image.

**Figure 9.**AIRSAR Flevoland classification maps of (

**a1**) SVM, (

**b1**) RF, (

**c1**) 1D-CNN, (

**d1**) 2D-CNN, (

**e1**) miniGCN, (

**f1**) FuNet, and (

**g1**) dual-branch FuNet. (

**a2**)–(

**g2**) Masked results according to the ground-truth of (

**a1**)–(

**g1**).

**Figure 10.**AIRSAR San Francisco classification maps of (

**a1**) SVM, (

**b1**) RF, (

**c1**) 1D-CNN, (

**d1**) 2D-CNN, (

**e1**) miniGCN, (

**f1**) FuNet, and (

**g1**) dual-branch FuNet. (

**a2**)–(

**g2**) Masked results according to the ground-truth of (

**a1**)–(

**g1**).

**Figure 11.**Classification OAs of superior networks with different training ratios on AIRSAR Flevoland data.

**Table 1.**Details of classes and training samples for AIRSAR Flevoland data (TR represents training ratio).

Class Number | Class Name | Train Number | Sample Number | TR (%) |
---|---|---|---|---|

1 | Stem beans | 62 | 6103 | 1.015894 |

2 | Peas | 92 | 9111 | 1.009768 |

3 | Forest | 150 | 14,944 | 1.003747 |

4 | Lucerne | 95 | 9477 | 1.002427 |

5 | Wheat | 173 | 17,283 | 1.000984 |

6 | Beet | 101 | 10,050 | 1.004975 |

7 | Potatoes | 153 | 15,292 | 1.000523 |

8 | Bare soil | 31 | 3078 | 1.007147 |

9 | Grass | 63 | 6269 | 1.004945 |

10 | Rapeseed | 127 | 12,690 | 1.000788 |

11 | Barley | 72 | 7156 | 1.006149 |

12 | Wheat2 | 106 | 10,591 | 1.00085 |

13 | Wheat3 | 214 | 21,300 | 1.004695 |

14 | Water | 135 | 13,476 | 1.001781 |

15 | Buildings | 5 | 476 | 1.05042 |

All | 1579 | 157,296 | 1.00384 |

**Table 2.**Details of classes and training samples for AIRSAR San Francisco data (TR represents training ratio).

Class Number | Class Name | Train Number | Sample Number | TR (%) |
---|---|---|---|---|

1 | Bare soil | 138 | 13,701 | 1.007226 |

2 | Mountain | 628 | 62,731 | 1.0011 |

3 | Water | 3296 | 329,566 | 1.000103 |

4 | Urban | 3428 | 342,795 | 1.000015 |

5 | Vegetation | 536 | 53,509 | 1.001701 |

All | 8026 | 802,302 | 1.000371 |

Layer | CNN | miniGCN |
---|---|---|

Input | 15 × 15 × 7 (Spatial feature) | 6 Polarimetric feature |

Block 1 | 2 × 2 Conv | BN |

BN | Graph Conv | |

2 × 2 Maxpool | BN | |

ReLU | ReLU | |

Output size | 8 × 8 × 30 | 120 |

Block 2 | 2 × 2 Conv | - |

BN | - | |

2 × 2 Maxpool | - | |

ReLU | - | |

Output size | 4 × 4 × 60 | - |

Block 3 | 2 × 2 Conv | - |

BN | - | |

ReLU | - | |

Output size | 4 × 4 × 120 | - |

Fully connected | FC Encoder | - |

BN | - | |

ReLU | - | |

Output size | 120 | - |

Fusion | FC Encoder | |

BN | ||

ReLU | ||

Output size | 240 | |

Output | FC Encoder | |

Softmax | ||

Output size | Number of classes |

**Table 4.**Detailed classification OAs and K of different algorithms compared to the proposed method on AIRSAR Flevoland. Bold numbers indicate the highest accuracy in each row.

Classes | Models | ||||||
---|---|---|---|---|---|---|---|

Name | SVM | RF | 1D-CNN | 2D-CNN | miniGCN | FuNet | Dual-Branch FuNet |

Stem beans | 80.95 | 80.90 | 79.59 | 99.47 | 66.33 | 99.47 | 99.35 |

Peas | 77.26 | 76.22 | 77.78 | 97.54 | 83.14 | 96.74 | 97.62 |

Forest | 77.13 | 85.36 | 76.65 | 96.69 | 96.62 | 96.43 | 98.33 |

Lucerne | 83.23 | 84.56 | 81.28 | 97.11 | 81.12 | 97.35 | 94.54 |

Wheat | 71.07 | 72.36 | 73.70 | 93.12 | 63.76 | 95.20 | 98.85 |

Beet | 77.80 | 79.85 | 83.08 | 94.34 | 71.39 | 94.18 | 98.05 |

Potatoes | 72.42 | 72.06 | 76.19 | 93.34 | 49.38 | 97.03 | 97.02 |

Bare soil | 66.26 | 68.00 | 81.29 | 100.00 | 56.58 | 100.00 | 94.58 |

Grass | 69.34 | 70.38 | 71.87 | 96.46 | 65.19 | 95.97 | 94.25 |

Rapeseed | 74.82 | 71.69 | 74.31 | 94.98 | 58.13 | 95.52 | 97.48 |

Barley | 70.99 | 76.96 | 78.67 | 98.09 | 83.54 | 98.90 | 97.52 |

Wheat2 | 71.11 | 69.38 | 71.71 | 96.73 | 42.84 | 97.15 | 97.47 |

Wheat3 | 90.18 | 89.64 | 89.86 | 99.67 | 78.32 | 99.21 | 99.75 |

Water | 96.45 | 96.78 | 92.93 | 99.00 | 99.91 | 99.03 | 98.94 |

Buildings | 65.82 | 68.79 | 77.28 | 80.68 | 83.86 | 86.20 | 91.93 |

OA (%) | 78.57 | 79.55 | 79.81 | 96.54 | 72.32 | 97.11 | 97.84 |

K (%) | 76.57 | 77.64 | 77.94 | 96.22 | 69.86 | 96.84 | 97.64 |

**Table 5.**Detailed classification OAs and K of different algorithms compared to the proposed method on AIRSAR San Francisco. Bold numbers indicate the highest accuracy in each row.

Classes | Models | ||||||
---|---|---|---|---|---|---|---|

Name | SVM | RF | 1D-CNN | 2D-CNN | miniGCN | FuNet | Dual-Branch FuNet |

Bare soil | 40.87 | 45.60 | 44.21 | 74.09 | 50.66 | 76.21 | 88.76 |

Mountain | 73.10 | 76.32 | 73.92 | 96.25 | 82.98 | 95.92 | 97.38 |

Water | 98.98 | 98.90 | 98.95 | 99.39 | 99.06 | 99.49 | 99.40 |

Urban | 94.88 | 94.46 | 94.92 | 94.93 | 48.36 | 96.80 | 98.68 |

Vegetation | 55.84 | 57.53 | 57.45 | 78.07 | 63.74 | 78.53 | 89.36 |

OA (%) | 91.33 | 91.57 | 91.57 | 95.39 | 72.95 | 96.27 | 98.09 |

K (%) | 86.22 | 86.65 | 86.62 | 92.79 | 62.05 | 94.14 | 97.00 |

**Table 6.**Classification OAs with different training ratios on AIRSAR Flevoland data. Bold numbers indicate the highest accuracy in each row.

Training Ratio (%) | SVM | RF | 1D-CNN | 2D-CNN | miniGCN | FuNet | Dual-Branch FuNet | |
---|---|---|---|---|---|---|---|---|

OA (%) | 1 | 78.57 | 79.55 | 79.81 | 96.54 | 72.32 | 97.11 | 97.84 |

5 | 81.95 | 83.43 | 82.59 | 98.7 | 75.52 | 98.66 | 99.67 | |

10 | 83.16 | 84.45 | 83.1 | 99.63 | 76.94 | 99.2 | 99.9 |

**Table 7.**Comparison of classification OAs with other studies on AIRSAR Flevoland data. Bold numbers indicate the highest accuracy in each row.

Training Ratio % | CV-CNN | Dual-Branch | 2D-CNN | MCFCNN | MEWGCN | Proposed | |
---|---|---|---|---|---|---|---|

OA (%) | 1 | 62 | 98.53 (75% TR) | 97.57 | 95.83 | - | 97.84 |

5 | 94 | 98.83 | - | 99.39 | 99.67 | ||

10 | 96.2 | 99.3 | - | - | 99.9 |

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Radman, A.; Mahdianpari, M.; Brisco, B.; Salehi, B.; Mohammadimanesh, F.
Dual-Branch Fusion of Convolutional Neural Network and Graph Convolutional Network for PolSAR Image Classification. *Remote Sens.* **2023**, *15*, 75.
https://doi.org/10.3390/rs15010075

**AMA Style**

Radman A, Mahdianpari M, Brisco B, Salehi B, Mohammadimanesh F.
Dual-Branch Fusion of Convolutional Neural Network and Graph Convolutional Network for PolSAR Image Classification. *Remote Sensing*. 2023; 15(1):75.
https://doi.org/10.3390/rs15010075

**Chicago/Turabian Style**

Radman, Ali, Masoud Mahdianpari, Brian Brisco, Bahram Salehi, and Fariba Mohammadimanesh.
2023. "Dual-Branch Fusion of Convolutional Neural Network and Graph Convolutional Network for PolSAR Image Classification" *Remote Sensing* 15, no. 1: 75.
https://doi.org/10.3390/rs15010075