基于域自适应的多源SAR图像分类方法

doi:10.7527/S1000-6893.2026.33015

Abstract

Abstract:

Convolutional Neural Networks （CNNs） have emerged as the dominant algorithms for object recognition in optical images. However， due to the complex imaging mechanism of Synthetic Aperture Radar （SAR）， labeled data is scarce and annotation costs are high， making it difficult to meet the demand of CNNs for large-scale， high-quality training data. Therefore， leveraging simulated or optical images for model training， and employing Unsupervised Domain Adaptation （UDA） techniques to bridge the domain gap between simulated or optical images and real SAR images， has become a viable solution. Nevertheless， existing UDA methods typically assume that all features from the source domain are transferable， overlooking the fact that domain-specific features may induce negative transfer. Meanwhile， noise inherent in pseudo-labels can also degrade the efficacy of domain alignment. To address these challenges， this paper proposes a domain adaptation framework that integrates feature disentanglement with label noise suppression. The framework employs a feature disentanglement module to decompose sample representations into transferable domain-invariant features and domain-specific features. By aligning only the domain-invariant features， the risk of negative transfer is effectively mitigated. Furthermore， a Weighted Generalized Cross Entropy （WGCE） loss function is designed to suppress noise interference arising during the iterative pseudo-labeling process. Experimental results on cross-domain SAR target recognition tasks demonstrate that the proposed method significantly enhances both recognition accuracy and the robustness of domain adaptation.

Key words: domain adaptation, multi-source remote sensing, image classification, synthetic aperture radar, label noise

CLC Number:

V475.9

Hongqiang WANG, Yuqing LAN, Fuzhan YUE, Zhenghuan XIA, Tao ZHANG. Multi-source SAR image classification method based on domain adaptation[J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(10): 533015.

Figures/Tables 9

Fig.1

Fig.2

Table 1

Table 2

Fig.3

Table 3

Table 4

Table 5

Fig.4

References 36

[1]	ZHANG J， LIU J， PAN B， et al. Domain adaptation based on correlation subspace dynamic distribution alignment for remote sensing image scene classification［J］. IEEE Transactions on Geoscience and Remote Sensing， 2020， 58（11）： 7920-7930.
[2]	吕小玲，仇晓兰，俞文明，等. 基于无监督域适应的仿真辅助SAR目标分类方法及模型可解释性分析［J］. 雷达学报， 2022， 11（1）： 168-182.
	LYU X L， QIU X L， YU W M， et al. Simulation-assisted SAR target classification based on unsupervised domain adaptation and model interpretability analysis［J］. Journal of Radars， 2022， 11（1）： 168-182 （in Chinese）.
[3]	TIRANDAZ Z， AKBARIZADEH G. A two-phase algorithm based on kurtosis curvelet energy and unsupervised spectral regression for segmentation of SAR images［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2016， 9（3）： 1244-1264.
[4]	LIN H P， SONG S L， YANG J. Ship classification based on MSHOG feature and task-driven dictionary learning with structured incoherent constraints in SAR images［J］. Remote Sensing， 2018， 10（2）： 190.
[5]	胡思茹，马福民，秦天奇，等. 基于多特征组合的红外舰船目标识别技术［J］. 舰船电子工程， 2022， 42（2）： 185-189.
	HU S R， MA F M， QIN T Q， et al. Infrared ship target recognition technology based on multi feature combination［J］. Ship Electronic Engineering， 2022， 42（2）： 185-189 （in Chinese）.
[6]	OUCHI K. Current status on vessel detection andclassification by synthetic aperture radar for maritimesecurity and safety［C］∥38th Symposium on Remote Sensingfor Environmental Sciences. 2016： 3-5.
[7]	ZHANG X， HUO C L， XU N， et al. Multitask learning for ship detection from synthetic aperture radar images［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2021， 14： 8048-8062.
[8]	张翼鹏，卢东东，仇晓兰，等. 基于散射点拓扑和双分支卷积神经网络的SAR图像小样本舰船分类［J］. 雷达学报， 2024， 13（2）： 411-427.
	ZHANG Y P， LU D D， QIU X L， et al. Few-shot ship classification of SAR images via scattering point topology and dual-branch convolutional neural network［J］. Journal of Radars， 2024， 13（2）： 411-427 （in Chinese）.
[9]	WANG H P， CHEN S Z， XU F， et al. Application of deep-learning algorithms to MSTAR data［C］∥2015 IEEE International Geoscience and Remote Sensing Symposium （IGARSS）. Piscataway： IEEE Press， 2015： 3743-3745.
[10]	HUANG Z L， DATCU M， PAN Z X， et al. Deep SAR-net： learning objects from signals［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2020， 161： 179-193.
[11]	CHEN J K， QIU X L， DING C B， et al. SAR image classification based on spiking neural network through spike-time dependent plasticity and gradient descent［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2022， 188： 109-124.
[12]	LI Y， DU L， WEI D. Multiscale CNN based on component analysis for SAR ATR［J］. IEEE Transactions on Geoscience and Remote Sensing， 2022， 60： 5211212.
[13]	SHI Y， DU L， LI C， et al. Unsupervised domain adaptation for SAR target classification based on domain-and class-level alignment： From simulated to real data［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2024， 207： 1-13.
[14]	LONG M S， ZHU H， WANG J M， et al. Deep transfer learning with joint adaptation networks［C］∥Proceedings of the 34th International Conference on Machine Learning. 2017： 2208-2217.
[15]	ZHU Y C， ZHUANG F Z， WANG J D， et al. Deep subdomain adaptation network for image classification［J］. IEEE Transactions on Neural Networks and Learning Systems， 2021， 32（4）： 1713-1722.
[16]	LONG M S， CAO Z J， WANG J M， et al. Conditional adversarial domain adaptation［C］∥Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018.
[17]	DU Z K， LI J J， SU H Z， et al. Cross-domain gradient discrepancy minimization for unsupervised domain adaptation［C］∥2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2021： 3936-3945.
[18]	GHIFARY M， KLEIJN W B， ZHANG M J， et al. Deep reconstruction-classification networks for unsupervised domain adaptation［C］∥Computer Vision-ECCV 2016. Cham： Springer， 2016： 597-613.
[19]	BOUSMALIS K， TRIGEORGIS G， SILBERMAN N， et al. Domain separation networks［C］∥30th Conference on Neural Information Processing Systems （NIPS 2016）. 2016.
[20]	SANKARANARAYANAN S， BALAJI Y， CASTILLO C D， et al. Generate to adapt： aligning domains using generative adversarial networks［C］∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2018： 8503-8512.
[21]	WANG S S， XIAO Q， WANG K Y， et al. Mutual-weighted feature disentanglement for unsupervised domain adaptation［J］. Multimedia Systems， 2024， 30（6）： 308.
[22]	ZHOU L H， YE M， LI X P， et al. Disentanglement then reconstruction： Unsupervised domain adaptation by twice distribution alignments［J］. Expert Systems with Applications， 2024， 237： 121498.
[23]	CAI R Y， JIN M， WEN Q S， et al. From entanglement to alignment： representation space decomposition for unsupervised time series domain adaptation［EB/OL］. （2025-08-06）［2025-10-01］： .
[24]	YU X， TSENG H H， YOO S， et al. INSURE： An information theory inspired disentanglement and purification model for domain generalization［J］. IEEE Transactions on Image Processing， 2024， 33： 3508-3519.
[25]	GAO F， PI D C， CHEN J F. Balanced and robust unsupervised open set domain adaptation via joint adversarial alignment and unknown class isolation［J］. Expert Systems with Applications， 2024， 238： 122127.
[26]	LI Y， ZHANG S S， LIU Y N， et al. Loose to compact feature alignment for domain adaptive object detection［J］. Pattern Recognition Letters， 2024， 181： 92-98.
[27]	LEWIS B， SCARNATI T， SUDKAMP E， et al. A SAR dataset for ATR development： The synthetic and measured paired labeled experiment （SAMPLE）［C］∥Algorithms for Synthetic Aperture Radar Imagery XXVI. 2019.
[28]	SHI Y， DU L， GUO Y C， et al. Unsupervised domain adaptation for ship classification via progressive feature alignment： from optical to SAR images［J］. IEEE Transactions on Geoscience and Remote Sensing， 2024， 62： 5222517.
[29]	HOU X Y， AO W， SONG Q， et al. FUSAR-Ship： building a high-resolution SAR-AIS matchup dataset of Gaofen-3 for ship detection and recognition［J］. Science China Information Sciences， 2020， 63： 140303.
[30]	GANIN Y， LEMPITSKY V. Unsupervised domain adaptation by backpropagation［C］∥Proceedings of the 32nd International Conference on Machine Learning. 2015： 1180-1189.
[31]	SHARMA A， KALLURI T， CHANDRAKER M. Instance level affinity-based transfer for unsupervised domain adaptation［C］∥2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2021： 5357-5367.
[32]	SUN B C， SAENKO K. Deep CORAL： Correlation alignment for deep domain adaptation［M］. Cham： Springer， 2016： 443-450.
[33]	ZHU Y C， ZHUANG F Z， WANG J D， et al. Multi-representation adaptation network for cross-domain image classification［J］. Neural Networks， 2019， 119： 214-221.
[34]	DAI S Y， CHENG Y， ZHANG Y Z， et al. Contrastively smoothed class alignment for unsupervised domain adaptation［C］∥Computer Vision-ACCV 2020. Cham： Springer， 2021： 268-283.
[35]	ZHANG Z L， SABUNCU M R. Generalized cross entropy loss for training deep neural networks with noisy labels［C］∥Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018.
[36]	SELVARAJU R R， COGSWELL M， DAS A， et al. Grad-CAM： Visual explanations from deep networks via gradient-based localization［J］. International Journal of Computer Vision， 2020， 128（2）： 336-359.

方法	Sample数据集准确率/%	Op2Real数据集准确率/%
DAN^［20］	82.53±1.02	61.85±1.97
DSAN^［21］	88.34±0.32	72.84±3.07
CDAN^［22］	84.48±0.54	64.95±3.90
DANN^［30］	84.36±1.91	64.40±1.55
ILA-DA^［31］	86.83±6.62	67.69±3.45
DeepCoral^［32］	72.67±2.21	56.81±1.26
MRAN^［33］	83.39±0.83	70.27±2.70
CoSCA^［34］	92.10±0.77	66.56±1.82
本文方法	96.10±1.14	78.02±1.45

数据集	L_MMD	L_WGCE	特征解耦	准确率/%
Sample	√			86.64
	√	√		90.72
	√		√	96.47
	√	√	√	97.40
Op2Real	√			73.60
	√	√		76.35
	√		√	76.61
	√	√	√	79.95

数据集	q	准确率/%
Sample	0.1	95.55
	0.3	98.70
	0.5	96.47
	0.7	97.22
	0.9	95.73
Op2Real	0.1	79.43
	0.3	79.17
	0.5	79.17
	0.7	77.38
	0.9	77.20

损失函数	Sample数据集			Op2Real数据集
噪声率/%	0	10	20	0	10	20
CE/%	97.59	94.81	92.21	82.01	77.12	76.09
L_WGCE/%	97.03	97.59	96.10	84.58	83.80	80.46

数据集	对齐特征		准确率/%
数据集	域不变特征	全部特征	准确率/%
Sample	√		97.40
Sample		√	92.58
Op2Real	√		79.95
Op2Real		√	74.81

Multi-source SAR image classification method based on domain adaptation

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 36

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Jianing JIN, Ling WANG, Rui GONG, Daiyin ZHU. 3D imaging of passive squint InISAR using target-borne illuminator of opportunity [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(8): 330982-330982.
[2]	Jinhu LÜ, Zongfu WANG, Kexin LIU, Jianglong YU, Deyuan LIU. New progress in cluster collaborative detection and guidance based on bi/multi-static SAR [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(6): 531548-531548.
[3]	Jing HE, Gewei TAN. High resolution imaging of moving targets based on ALPFT parameter estimation [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(1): 330502-330502.
[4]	Li YAN, Jie ZHANG, Jiadong WANG. [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(S1): 730559-730559.
[5]	Zheng YE, Daiyin ZHU, Di WU. SAR image registration algorithm based on echo information of overlapping subaperture [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(8): 327254-327254.
[6]	Gongye YU, Weidong CAI, Minghui HU, Wencai LIU, Bo MA. Intelligent migration diagnosis of mechanical faults driven by hybrid fault mechanism and domain adaptation [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(2): 426800-426800.
[7]	Penghui JI, Shiqi XING, Dahai DAI, Bo Pang, Dejun FENG. A SAR scene deceptive jamming method based on range convolution and azimuth multiplication modulation [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(18): 328235-328235.
[8]	Lianzi WANG, Ling WANG, Daiyin ZHU. An ISAR autofocus imaging algorithm based on FCN and transfer learing [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(17): 328172-328172.
[9]	BAO Yue, CHEN Junyu, SHI Tianyue, MAO Xinhua. Error model-aided autofocus for airborne high resolution wide swath DBF-SAR [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(6): 324502-324502.
[10]	SONG Chuang, ZHAO Jiajia, WANG Kang, LIANG Xinkai. A survey of few shot learning based on intelligent perception [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(S1): 723756-723756.
[11]	LU Jingyue, ZHANG Lei, MENG Zhichao, SHENG Jialian. Unambiguous imaging for forward-looking synthetic aperture radar on curve trajectory [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2019, 40(7): 322745-322745.
[12]	ZHU Xiaoxiu, HU Wenhua, MA Juntao, GUO Baofeng, XUE Dongfang. ISAR autofocusing imaging with sparse apertures and time-varying bistatic angle [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2018, 39(8): 322059-322059.
[13]	TANG Zhengzhao, DONG Chunxi, CHANG Xin, LIU Mingming, ZHAO Guoqing. ISAR micro-Doppler scatter-wave jamming method based on towed jammer [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2018, 39(7): 322007-322007.
[14]	WAN Jun, ZHOU Yu, ZHANG Linrang, CHEN Zhanye. A fast SAR-GMTI focusing method based on time reversal and reduced-order Keystone [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2018, 39(6): 321862-321862.
[15]	YANG Mingdong, YU Xiang, ZHU Daiyin. High-precision space-variant motion compensation with multi-level processing for airborne SAR based on subswath [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2018, 39(2): 321557-321557.