跨模态渐进式知识迁移SAR目标检测技术

赵国威; 蒋嘉庆; 董刚刚

doi:10.12263/DZXB.20250417

您当前的位置：

首页 >

文章列表页 >

跨模态渐进式知识迁移SAR目标检测技术

学术论文 | 更新时间：2025-12-27

- 跨模态渐进式知识迁移SAR目标检测技术
- Cross-Modal SAR Target Detection via Progressive Knowledge Transfer
- 电子学报 2025年53卷第9期页码：3147-3162
- 作者机构：
  
  西安电子科技大学雷达信号处理全国重点实验室，陕西西安 710071
- 作者简介：
  
  [ "赵国威男，2000年3月出生于山东省枣庄市.现为西安电子科技大学信息与通信工程专业硕士研究生.主要研究方向为雷达信号处理、目标检测识别. Email: gwzhao0321@163.com" ]
  [ "蒋嘉庆男，2002年10月出生于河北省任丘市.现为西安电子科技大学信息与通信工程专业硕士研究生.主要研究方向为SAR干扰抑制与目标检测. E-mail: 15613785520@163.com" ]
  [ "董刚刚男，1982年11月出生于陕西省西安市.现为西安电子科技大学教授、博士生导师.2012年和2016年获得国防科技大学工学硕士与博士学位.主要研究方向为雷达成像、目标检测识别、遥感图像解译等.E-mail: dongganggang@nudt.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(61971324;62525105)
- DOI：10.12263/DZXB.20250417
  中图分类号： TN95;
- 收稿：2025-05-25，
  
  录用：2025-08-13，
  
  纸质出版：2025-09-25
- 稿件说明：
移动端阅览
赵国威, 蒋嘉庆, 董刚刚. 跨模态渐进式知识迁移SAR目标检测技术[J]. 电子学报, 2025, 53(09): 3147-3162.

ZHAO Guo-wei, JIANG Jia-qing, DONG Gang-gang. Cross-Modal SAR Target Detection via Progressive Knowledge Transfer[J]. Acta Electronica Sinica, 2025, 53(09): 3147-3162.
赵国威, 蒋嘉庆, 董刚刚. 跨模态渐进式知识迁移SAR目标检测技术[J]. 电子学报, 2025, 53(09): 3147-3162. DOI：10.12263/DZXB.20250417

ZHAO Guo-wei, JIANG Jia-qing, DONG Gang-gang. Cross-Modal SAR Target Detection via Progressive Knowledge Transfer[J]. Acta Electronica Sinica, 2025, 53(09): 3147-3162. DOI：10.12263/DZXB.20250417

摘要

随着光/SAR传感器的投入使用，如何挖掘异源数据信息、提高遥感图像解译与信息获取效率，是当前亟待解决的科学问题.对此，论文提出了一种基于光/SAR（Synthetic Aperture Radar）图像渐进式知识迁移的跨模态目标检测方法（Progressive Crossmodal Knowledge Transfer，PCKT），充分挖掘可见光图像丰富的纹理细节信息，改善SAR图像目标检测性能.第一，针对可见光遥感与SAR截然不同的成像机理导致模态差异大、信息融合难的问题，提出从可见光图像到SAR图像的跨域生成技术，利用可见光图像语义信息引导构建伪SAR中间域，实现光学辐射特征与SAR散射特性的语义融合；第二，针对可见光与SAR图像之间存在的语义鸿沟、跨模态学习效果差的问题，设计光/SAR多尺度特征对齐学习策略，实现可见光源域-伪SAR中间域语义特征、伪SAR中间域-SAR目标域散射特性分布的高效对齐，形成分阶段的跨模态知识迁移学习框架；第三，针对光/SAR模态离群样本对跨模态学习的不利影响，提出基于质量感知的动态权重分配机制，根据域分类器置信度衡量动态量化合成样本的可靠性，在训练过程中优先学习高置信度样本，从而抑制离群中间域图像产生的不利影响.最后，利用SpaceNet6、SSDD（SAR Ship Detection Dataset）、HRSID（High-Resolution SAR Images Dataset）等典型异源数据进行了大量跨模态学习实验验证，结果表明所提方法能充分挖掘可见光图像的重要信息，改善SAR图像目标检测效果，与源域无迁移方法相比，论文所提出方法在SpaceNet同源知识迁移结果提升平均检测精度为21.5个百分点，与次优基线方法相比平均检测精度提升为3.3个百分点，很好地验证了跨模态知识迁移在SAR目标检测任务中的可行性.

Abstract

The wide application of electro-optical sensors presented the urgent need of cross-modal learning between optical and SAR image. In this paper

a new cross-modal synthetic aperture radar (SAR) target detection method via progressive knowledge transfer was proposed. First

a new generative technique from the optical image to SAR image was presented. The immediate domain composed of the generated pseudo SAR images can be formed accordingly. The semantic discrepancies between SAR backscattering imaging mechanism and the passive optical radiation imagery can be bridged. The optical radiation features with SAR scattering characteristics can be fused effectively. Second

a dual-stage domain adaptation strategy composed of the multi-scale feature alignment skill was presented. The semantic components between the optical source domain and the intermediate domain can be aligned through the multi-scale feature learning trick initially. The scattering distribution alignment between the intermediate domain and the SAR target domain can be then achieved. Third

a quality-aware dynamic weighting strategy was presented to mitigate the impact of outlier samples in the intermediate domain. It was capable of adjusting the contributions of synthetic data based on confidence metrics dynamically. Finally

multiple rounds of experiments were pursued on SpaceNet6

SSDD (SAR Ship Detection Dataset)

and HRSID (High-Resolution SAR Images Dataset) datasets. The results proved the advantages of proposed method. The improvement of 21.5 percentage points was achieved compared to the source-only learning method. Likewise

the improvement of 3.3 percentage points was achieved in comparison to the state-of-the-art. These results confirm the viability of electro-optical-to-SAR knowledge transfer for enhancing cross-modal target detection.

关键词

Keywords

references

孙琦钰 , 赵超强 , 唐漾 , 等 . 基于无监督域自适应的计算机视觉任务研究进展 [J ] . 中国科学: 技术科学 , 2022 , 52 ( 1 ): 26 - 54 .

SUN Q Y , ZHAO C Q , TANG Y , et al . A survey on unsupervised domain adaptation in computer vision tasks [J ] . Scientia Sinica (Technologica) , 2022 , 52 ( 1 ): 26 - 54 . (in Chinese)

郭倩 , 王海鹏 , 徐丰 . SAR图像飞机目标检测识别进展 [J ] . 雷达学报 , 2020 , 9 ( 3 ): 497 - 513 .

GUO Q , WANG H P , XU F . Research progress on aircraft detection and recognition in SAR imagery [J ] . Journal of Radars , 2020 , 9 ( 3 ): 497 - 513 . (in Chinese)

方澄 , 管方恒 , 李天驰 , 等 . 端到端全复数域SAR目标分类神经网络 [J ] . 电子学报 , 2024 , 52 ( 7 ): 2449 - 2460 .

FANG C , GUAN F H , LI T C , et al . End-to-end full complex-valued domain SAR target classification neural network [J ] . Acta Electronica Sinica , 2024 , 52 ( 7 ): 2449 - 2460 . (in Chinese)

DE MAIO A , AUBRY A . Radar detection, performance analysis, and CFAR techniques [C ] // 2019 IEEE Radar Conference . Piscataway : IEEE , 2019 : 1 - 120 .

罗会兰 , 陈鸿坤 . 基于深度学习的目标检测研究综述 [J ] . 电子学报 , 2020 , 48 ( 6 ): 1230 - 1239 .

LUO H L , CHEN H K . Survey of object detection based on deep learning [J ] . Acta Electronica Sinica , 2020 , 48 ( 6 ): 1230 - 1239 . (in Chinese)

刘颖 , 刘红燕 , 范九伦 , 等 . 基于深度学习的小目标检测研究与应用综述 [J ] . 电子学报 , 2020 , 48 ( 3 ): 590 - 601 .

LIU Y , LIU H Y , FAN J L , et al . A survey of research and application of small object detection based on deep learning [J ] . Acta Electronica Sinica , 2020 , 48 ( 3 ): 590 - 601 . (in Chinese)

GIRSHICK R , DONAHUE J , DARRELL T , et al . Rich feature hierarchies for accurate object detection and semantic segmentation [C ] // 2014 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2014 : 580 - 587 .

GIRSHICK R . Fast R-CNN [C ] // 2015 IEEE International Conference on Computer Vision . Piscataway : IEEE , 2016 : 1440 - 1448 .

REN S Q , HE K M , GIRSHICK R , et al . Faster R-CNN: Towards real-time object detection with region proposal networks [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , 39 ( 6 ): 1137 - 1149 .

REDMON J , DIVVALA S , GIRSHICK R , et al . You only look once: Unified, real-time object detection [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2016 : 779 - 788 .

LIU W , ANGUELOV D , ERHAN D , et al . SSD: Single shot multiBox detector [M ] // Computer Vision-ECCV 2016 . Cham : Springer International Publishing , 2016 : 21 - 37 .

LIN Z , JI K F , LENG X G , et al . Squeeze and excitation rank faster R-CNN for ship detection in SAR images [J ] . IEEE Geoscience and Remote Sensing Letters , 2019 , 16 ( 5 ): 751 - 755 .

ZHAO Y , ZHAO L J , XIONG B L , et al . Attention receptive pyramid network for ship detection in SAR images [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2020 , 13 : 2738 - 2756 .

KANG M , JI K F , LENG X G , et al . Contextual region-based convolutional neural network with multilayer fusion for SAR ship detection [J ] . Remote Sensing , 2017 , 9 ( 8 ): 860 .

夏勇 , 田西兰 , 常沛 , 等 . 基于深度学习的复杂沙漠背景SAR目标检测 [J ] . 雷达科学与技术 , 2019 , 17 ( 3 ): 305 - 309, 318 .

XIA Y , TIAN X L , CHANG P , et al . SAR target detection in complex desert background images based on deep learning [J ] . Radar Science and Technology , 2019 , 17 ( 3 ): 305 - 309, 318 . (in Chinese)

谢兆哲 , 程永强 , 吴昊 , 等 . 基于Toeplitz矩阵特征值分解的SAR图像舰船目标检测方法 [J ] . 信号处理 , 2023 , 39 ( 3 ): 496 - 504 .

XIE Z Z , CHENG Y Q , WU H , et al . Ship target detection method in SAR imagery based on eigenvalue decomposition of the toeplitz matrix [J ] . Journal of Signal Processing , 2023 , 39 ( 3 ): 496 - 504 . (in Chinese)

程旭东 , 史彩娟 , 高炜翔 , 等 . 面向域自适应目标检测的一致无偏教师模型 [J ] . 图学学报 , 2025 , 46 ( 1 ): 114 - 125 .

CHENG X D , SHI C J , GAO W X , et al . Consistent and unbiased teacher model research for domain adaptive object detection [J ] . Journal of Graphics , 2025 , 46 ( 1 ): 114 - 125 . (in Chinese)

张鸿杰 , 李昂 , 过洁 , 等 . 基于风格迁移及对抗加权的开放集域自适应 [J ] . 计算机科学技术学报 , 2023 , 38 ( 3 ): 644 - 658 .

胡逸雯 , 刘鑫 , 匡翠方 , 等 . 基于深度学习的自适应光学技术研究进展及展望 [J ] . 中国激光 , 2023 , 50 ( 11 ): 1101009 .

HU Y W , LIU X , KUANG C F , et al . Research progress and prospect of adaptive optics based on deep learning [J ] . Chinese Journal of Lasers , 2023 , 50 ( 11 ): 1101009 . (in Chinese)

刘建伟 , 孙正康 , 罗雄麟 . 域自适应学习研究进展 [J ] . 自动化学报 , 2014 , 40 ( 8 ): 1576 - 1600 .

LIU J W , SUN Z K , LUO X L . Review and research development on domain adaptation learning [J ] . Acta Automatica Sinica , 2014 , 40 ( 8 ): 1576 - 1600 . (in Chinese)

周洋 , 韩冰 , 高新波 , 等 . 基于注意力机制和循环域三元损失的域自适应目标检测 [J ] . 自动化学报 , 2024 , 50 ( 11 ): 2188 - 2203 .

ZHOU Y , HAN B , GAO X B , et al . Domain adaptive object detection based on attention mechanism and cycle domain triplet loss [J ] . Acta Automatica Sinica , 2024 , 50 ( 11 ): 2188 - 2203 . (in Chinese)

胡杰 , 徐博远 , 熊宗权 , 等 . 基于多尺度掩码分类域自适应网络的跨域目标检测算法 [J ] . 汽车工程 , 2022 , 44 ( 9 ): 1327 - 1338 .

HU J , XU B Y , XIONG Z Q , et al . Cross-domain object detection algorithm based on multi-scale mask classification domain adaptive network [J ] . Automotive Engineering , 2022 , 44 ( 9 ): 1327 - 1338 . (in Chinese)

李威 , 王蒙 . 基于渐进多源域迁移的无监督跨域目标检测 [J ] . 自动化学报 , 2022 , 48 ( 9 ): 2337 - 2351 .

LI W , WANG M . Unsupervised cross-domain object detection based on progressive multi-source transfer [J ] . Acta Automatica Sinica , 2022 , 48 ( 9 ): 2337 - 2351 . (in Chinese)

KHODABANDEH M , VAHDAT A , RANJBAR M , et al . A robust learning approach to domain adaptive object detection [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2019 : 480 - 490 .

KIM S , CHOI J , KIM T , et al . Self-training and adversarial background regularization for unsupervised domain adaptive one-stage object detection [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2019 : 6091 - 6100 .

FRENCH G , MACKIEWICZ M , FISHER M . Self-ensembling for visual domain adaptation [EB/OL ] . ( 2018-09-23 )[ 2025-03-25 ] . https://arXiv.org/abs/1706.05208 https://arXiv.org/abs/1706.05208 .

SOHN K , BERTHELOT D , CARLINI N , et al . Fixmatch: Simplifying semi-supervised learning with consistency and confidence [J ] . Advances in Neural Information Processing Systems , 2020 , 33 : 596 - 608 .

LI Y J , DAI X L , MA C Y , et al . Cross-domain adaptive teacher for object detection [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 7571 - 7580 .

CAO S C , JOSHI D , GUI L Y , et al . Contrastive mean teacher for domain adaptive object detectors [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2023 : 23839 - 23848 .

BAI Y F , WU Y Q , ZHU B , et al . Contrastive-domain mean teacher for domain adaptive object detection [J ] . IEEE Transactions on Circuits and Systems for Video Technology , 2025 : 3575205 .

CHEN L , HAN J H , WANG Y P . DATR: Unsupervised domain adaptive detection transformer with dataset-level adaptation and prototypical alignment [J ] . IEEE Transactions on Image Processing , 2025 , 34 : 982 - 994 .

CHEN Y H , LI W , SAKARIDIS C , et al . Domain adaptive faster R-CNN for object detection in the wild [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 3339 - 3348 .

SAITO K , USHIKU Y , HARADA T , et al . Strong-weak distribution alignment for adaptive object detection [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 6949 - 6958 .

ZHANG H , LUO G Y , CAO Y , et al . Scale-disentangled and uncertainty-guided alignment for domain-adaptive object detection [J ] . IEEE Transactions on Intelligent Transportation Systems , 2024 , 25 ( 12 ): 19507 - 19521 .

BELAL A , MEETHAL A , ROMERO F P , et al . Multi-source domain adaptation for object detection with prototype-based mean teacher [C ] // 2024 IEEE/CVF Winter Conference on Applications of Computer Vision . Piscataway : IEEE , 2024 : 1266 - 1275 .

ARRUDA V F , PAIXÃO T M , BERRIEL R F , et al . Cross-domain car detection using unsupervised image-to-image translation: From day to night [C ] // 2019 International Joint Conference on Neural Networks . Piscataway : IEEE , 2019 : 1 - 8 .

CHEN M , RADFORD A , CHILD R , et al . Generative pretraining from pixels [C ] // Proceedings of the 37th International Conference on Machine Learning . New York : ACM , 2020 : 1691 - 1703 .

HSU H K , YAO C-H , TSAI Y H , et al . Progressive domain adaptation for object detection [C ] // 2020 IEEE Winter Conference on Applications of Computer Vision . Piscataway : IEEE , 2020 : 738 - 746 .

SHI Y , DU L , GUO Y C . Unsupervised domain adaptation for SAR target detection [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2021 , 14 : 6372 - 6385 .

DU Z P , SHIT M , DENG J K . Boosting object detection with zero-shot day-night domain adaptation [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 12666 - 12676 .

姚琴风 , 宁永香 , 杜孙稳 . 基于域自适应神经网络的光学与合成孔径雷达遥感图像变化检测 [J ] . 激光与光电子学进展 , 2024 , 61 ( 18 ): 255 - 264 .

YAO Q F , NING Y X , DU S W . Change detection of optical and synthetic aperture radar remote sensing images based on a domain adaptive neural network [J ] . Laser & Optoelectronics Progress , 2024 , 61 ( 18 ): 255 - 264 . (in Chinese)

季鼎承 , 蒋亦樟 , 王士同 . 基于域与样例平衡的多源迁移学习方法 [J ] . 电子学报 , 2019 , 47 ( 3 ): 692 - 699 .

JI D C , JIANG Y Z , WANG S T . Multi-source transfer learning method by balancing both the domains and instances [J ] . Acta Electronica Sinica , 2019 , 47 ( 3 ): 692 - 699 . (in Chinese)

余游 , 冯林 , 王格格 , 等 . 一种基于伪标签的半监督少样本学习模型 [J ] . 电子学报 , 2019 , 47 ( 11 ): 2284 - 2291 .

YU Y , FENG L , WANG G G , et al . A few-shot learning model based on semi-supervised with pseudo label [J ] . Acta Electronica Sinica , 2019 , 47 ( 11 ): 2284 - 2291 . (in Chinese)

TIAN Z Z , WANG W , ZHOU K , et al . Weighted pseudo-labels and bounding boxes for semisupervised SAR target detection [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2024 , 17 : 5193 - 5203 .

VAN DER MAATEN L , HINTON G . Visualizing data using t-SNE [J ] . Journal of Machine Learning Research , 2008 , 9 ( 86 ): 2579 - 2605 .

SUN B C , SAENKO K . Deep CORAL: Correlation alignment for deep domain adaptation [M ] // Computer Vision-ECCV 2016 Workshops . Cham : Springer International Publishing , 2016 : 443 - 450 .

LITTLE TODD D . The Oxford Handbook of Quantitative Methods in Psychology: Vol . 2 : Statistical Analysis [M ] . Oxford : Oxford University Press , 2013: 458 - 485 .

SHERMEYER J , HOGAN D , BROWN J , et al . SpaceNet 6: Multi-sensor all weather mapping dataset [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops . Piscataway : IEEE , 2020 : 768 - 777 .

ZHANG T W , ZHANG X L , LI J W , et al . SAR ship detection dataset (SSDD): Official release and comprehensive data analysis [J ] . Remote Sensing , 2021 , 13 ( 18 ): 3690 .

WEI S J , ZENG X F , QU Q Z , et al . HRSID: A high-resolution SAR images dataset for ship detection and instance segmentation [J ] . IEEE Access , 2020 , 8 : 120234 - 120254 .

CHEN C Q , ZHENG Z B , DING X H , et al . Harmonizing transferability and discriminability for adapting object detectors [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 8866 - 8875 .

JIANG J , CHEN B , WANG J , et al . Decoupled adaptation for cross-domain object detection [C ] // The Tenth International Conference on Learning Representations . Vivtual Event : ICLR , 2022 : 1 - 16 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

SAR图像舰船及其尾迹检测研究综述

基于对抗学习和增强优化的深度转换语音还原方法

基于条件变分推断与内省对抗学习的多样化图像描述生成

端到端全复数域SAR目标分类神经网络