DE-MFM-YOLO: A YOLO-Based Network with Detail-Enhanced Convolution and Modulated Feature Fusion for Multi-Scale Ship Detection in SAR Images
Main Article Content
Abstract
Synthetic Aperture Radar (SAR) plays an important role in maritime ship detection due to its all-weather and day-and-night imaging capability. However, reliable detection remains challenging because of strong speckle noise, complex sea clutter, and the weak representation of small ship targets. To address these issues, this paper proposes DE-MFM-YOLO, an efficient SAR ship detection framework based on YOLOv11. The proposed framework enhances local edge and texture representation through Detail-Enhanced Convolution (DEConv) and introduces a Modulation Fusion Module (MFM) to adaptively fuse multi-scale features and improve semantic interaction across different feature levels. Experimental results on the HRSID dataset demonstrate that DE-MFM-YOLO achieves an AP50 of 93.0% while maintaining real-time inference capability. The complementary integration of DEConv and MFM effectively improves feature representation, multi-scale feature aggregation, and the detection of small and densely distributed ship targets. These results indicate that the proposed method provides an effective balance between detection accuracy and computational efficiency for practical SAR maritime monitoring applications.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
F. S. Paolo, D. Kroodsma, J. Raynor, T. Hochberg, P. Davis, J. Cleary, L. Marsaglia, S. Orofino, C. Thomas, and P. Halpin, “Satellite mapping reveals extensive industrial activity at sea,” Nature, vol. 625, pp. 85–91, 2024, doi: 10.1038/s41586-023-06825-8.
L. Min, F. Dou, Y. Zhang, D. Shao, L. Li, and B. Wang, “CM-YOLO: Context Modulated Representation Learning for Ship Detection,” IEEE Trans. Geosci. Remote Sens., vol. 63, Art. no. 4202414, 2025, doi: 10.1109/TGRS.2025.3538848.
C. Alexandre, R. Devillers, D. Mouillot, R. Seguin, and T. Catry, “Ship Detection with SAR C-Band Satellite Images: A Systematic Review,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 17, pp. 14353– 14367, 2024, doi: 10.1109/JSTARS.2024.3437187.
M. J. Er, Y. Zhang, J. Chen, and W. Gao, “Ship detection with deep learning: A survey,” Artif. Intell. Rev., vol. 56, pp. 11825–11865, 2023, doi: 10.1007/s10462-023-10455-x.
Y. Li et al., “Ship Detection and Classification Based on Cascaded Detection of Hull and Wake from Optical Satellite Remote Sensing Imagery,” GISci. Remote Sens., vol. 60, Art. no. 2196159, 2023, doi: 10.1080/15481603.2023.2196159.
Z. Liu, J. Lyu, and Y. Fu, “Scattering-Guided Class-Irrelevant Filtering for Adversarially Robust SAR Automatic Target Recognition,” Signal Process., vol. 239, Art. no. 110273, 2026, doi: 10.1016/j.sigpro.2025.110273.
Z. Wang, R. Wang, J. Ai, F. Yang, and Y. Zhou, “Global and Local Context-Aware Ship Detector for High-Resolution SAR Images,” IEEE Trans. Aerosp. Electron. Syst., vol. 59, pp. 4159–4167, 2023, doi: 10.1109/TA ES.2023.3237520.
J. Li et al., “Small Ship Detection Based on Improved Neural Network Algorithm and SAR Images,” Remote Sens., vol. 17, Art. no. 2586, 2025, doi: 10.3390/rs17152586.
S. Baraha et al., “CNN-Augmented SAR Image Despeckling Using Modified Speckle Reducing Anisotropic Diffusion and Discrete Wavelet Transform,” Signal Process. Image Commun., vol. 138, Art. no. 117380, 2025, doi: 10.1016/j.image.2025.117380.
S. Li, H. Wei, Y. Mao, and J. Fan, “A Novel Two-Stage Superpixel CFAR Method Based on Truncated KDE Model for Target Detection in SAR Images,” Electronics, vol. 14, Art. no. 1327, 2025, doi: 10.3390/electr onics14071327.
S. Sun and J. Wang, “Ship Detection in SAR Images Based on Steady CFAR Detector and Knowledge-Oriented GBDT Classifier,” Electronics, vol. 13, Art. no. 2692, 2024, doi: 10.3390/electronics13142692.
L. Zhang, Z. Zhang, S. Lu, D. Xiang, and Y. Su, “Fast Superpixel-Based Non-Window CFAR Ship Detector for SAR Imagery,” Remote Sens., vol. 14, Art. no. 2092, 2022, doi: 10.3390/rs14092092.
N. Li, X. Pan, L. Yang, Z. Huang, Z. Wu, and G. Zheng, “Adaptive CFAR Method for SAR Ship Detection Using Intensity and Texture Feature Fusion Attention Contrast Mechanism,” Sensors, vol. 22, Art. no. 8116, 2022, doi: 10.3390/s22218116.
J. Li, C. Xu, H. Su, L. Gao, and T. Wang, “Deep learning for SAR ship detection: Past, present and future,” Remote Sens., vol. 14, Art. no. 2712, 2022, doi: 10.3390/rs14112712.
S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, pp. 1137–1149, 2017, doi: 10.1109/TPAMI.2016.2577031.
Q. Shuai and X. Wu, “Object detection system based on SSD algorithm,” in Proc. Int. Conf. Culture-Oriented Sci. Technol., Beijing, China, 2020, pp. 141–144, doi: 10.1109/ICCST50977.2020.00033.
J. Cheng et al., “A feature enhanced RetinaNet-based for instance-level ship recognition,” Eng. Appl. Artif. Intell., vol. 126, Art. no. 107133, 2023, doi: 10.1016/j.engappai.2023.107133.
M. Zhu et al., “A novel anchor-free method based on FCOS + ATSS for ship detection in SAR images,” Remote Sens., vol. 14, Art. no. 2034, 2022, doi: 10.3390/rs14092034.
Q. Cao et al., “LH-YOLO: A Lightweight and High-Precision SAR Ship Detection Model Based on the Improved YOLOv8n,” Remote Sens., vol. 16, Art. no. 4340, 2024, doi: 10.3390/rs16224340.
C. Yu and Y. Shin, “SMEP-DETR: Transformer-Based Ship Detection for SAR Imagery with Multi-Edge Enhancement and Parallel Dilated Convolutions,” Remote Sens., vol. 17, Art. no. 953, 2025, doi: 10.3390/rs17060953.
X. Zhu, W. Su, L. Lu, B. Li, X. Wang, and J. Dai, “Deformable DETR: Deformable Transformers for End-to-End Object Detection,” arXiv preprint arXiv:2010.04159, 2020.
Z. Hong et al., “Multi-scale ship detection from SAR and optical imagery via a more accurate YOLOv3,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 14, pp. 6083–6101, 2021, doi: 10.1109/JSTARS.2021.3087555.
S. Liu, P. Chen, and Y. Zhang, “A multiscale feature pyramid SAR ship detection network with robust background interference,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 16, pp. 9904–9915, 2023, doi: 10.1109/JSTARS.2023.3325376.
J. Chen et al., “LKPF-YOLO: A Small Target Ship Detection Method for Marine Wide-Area Remote Sensing Images,” IEEE Trans. Aerosp. Electron. Syst., vol. 60, pp. 8482–8496, 2024.
J. Si et al., “Maritime ship detection method for satellite images based on multiscale feature fusion,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 16, pp. 6642- 6655, 2023, doi: 10.1109/JSTARS.2023.3296898.
R. L. Rocha and F. A. P. de Figueiredo, “Enhancing YOLO-Based SAR Ship Detection with Attention Mechanisms,” Remote Sens., vol. 17, Art. no. 3170, 2025, doi: 10.3390/rs17183170.
Y. Chen et al., “AJANet: SAR Ship Detection Network Based on Adaptive Channel Attention and Large Separable Kernel Adaptation,” Remote Sens., vol. 17, Art. no. 1745, 2025, doi: 10.3390/rs17101745.
M. Zhang, X. Rong, and X. Yu, “Light-SDNet: A lightweight CNN architecture for ship detection,” IEEE Access, vol. 10, pp. 86647–86662, 2022, doi: 10.1109/ACCESS.2022.3199352.
P. Huang et al., “IA-CIoU: An improved IoU bounding box loss function for SAR ship target detection methods,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 17, pp. 10569–10582, 2024, doi: 10.1109/JSTARS.202 4.3402540.
R. Khanam and M. Hussain, “YOLOv11: An overview of the key architectural enhancements,” arXiv preprint arXiv:2410.17725, 2024.
S. Wei, X. Zeng, Q. Qu, M. Wang, H. Su, and J. Shi, “HRSID: A High-Resolution SAR Images Dataset for Ship Detection and Instance Segmentation,” IEEE Access, vol. 8, pp. 120234–120254, 2020, doi: 10.1109/ACCESS.2020.3005861.
T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature Pyramid Networks for Object Detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Honolulu, HI, USA, 2017, pp. 2117–2125, doi: 10.1109/CVPR.2017.106.
Z. Chen, Y. Zhang, J. Gu, L. Kong, X. Yang, and F. Yu, “DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention,” in Proc. AAAI Conf. Artif. Intell. (AAAI), vol. 38, 2024, pp. 1234–1242.
Y. Liu, H. Zhao, X. Wang, J. Li, and Q. Zhang, “Depth Information Assisted Collaborative Mutual Promotion Network for Single Image De-hazing,” IEEE Trans. Multimedia, vol. 26, pp. 5842–5855, 2024.
T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal Loss for Dense Object Detection,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Venice, Italy, 2017, pp. 2980–2988, doi: 10.1109/ICCV.2017.324.
Z. Tian, C. Shen, H. Chen, and T. He, “FCOS: Fully Convolutional One-Stage Object Detection,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Seoul, South Korea, 2019, pp. 9627–9636, doi: 10.1109/ICCV.2019.0097 2.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Las Vegas, NV, USA, 2016, pp. 779–788, doi: 10.1109/CVPR.2016.91.
X. Ma, X. Dai, Y. Bai, Y. Wang, and Y. Fu, “Rewrite the Stars,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Seattle, WA, USA, 2024, pp. 5694–5703, doi: 10.1109/CVPR52733.2024.00544.
L. Kong, J. Dong, J. Ge, M. Li, and J. Pan, “Efficient Frequency Domain-Based Transformers for High-Quality Image Deblurring,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Vancouver, BC, Canada, 2023, pp. 5886–5895, doi: 10.1109/CVPR52729.2023.00570.
H. Li et al., “Slim-Neck by GSConv: A Lightweight Design for Real-Time Detector Architectures,” J. Real-Time Image Process., vol. 21, Art. no. 62, 2024, doi: 10.1007/s11554-024-01436-6.
Y. Si et al., “SCSA: Exploring the synergistic effects between spatial and channel attention,” Neurocomputing, vol. 634, Art. no. 129866, 2025, doi: 10.1016/j.neucom.2025.129866.
T. Zhang et al., “SAR ship detection dataset (SSDD): Official release and comprehensive data analysis,” Remote Sens., vol. 13, Art. no. 3690, 2021, doi: 10.3390/rs13183690.
Y. Zhao et al., “DETRs Beat YOLOs on Real-Time Object Detection,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Seattle, WA, USA, 2024, pp. 16965–16974, doi: 10.1109/CVPR52733.2024.016 05.
C.-Y. Wang, I.-H. Yeh, and H.-Y. M. Liao, “YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2024, doi: 10.1007/978-3-031-72751-1_1.
A. Wang et al., “YOLOv10: Real-Time End-to-End Object Detection,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 37, 2024, pp. 107984– 108011, doi: 10.52202/079017-3429.
Y. Tian, Q. Ye, and D. Doermann, “YOLOv12: Attention-Centric Real-Time Object Detectors,” arXiv preprint arXiv:2502.12524, 2025.
P. Qin et al., “Multilayer feature extraction network for military ship detection from high-resolution optical remote sensing images,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 14, pp. 11058–11069, 2021, doi: 10.1109/JSTARS.2021.3123080.
K. Zhou et al., “Ship detection in SAR images based on multi-scale feature extraction and adaptive feature fusion,” Remote Sens., vol. 14, Art. no. 755, 2022, doi: 10.3390/rs14030755.
Y. Zhao et al., “Attention receptive pyramid network for ship detection in SAR images,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 13, pp. 2738–2756, 2020, doi: 10.1109/JSTARS.2020.2997081.
Z. Wang et al., “Global and local context-aware ship detector for high-resolution SAR images,” IEEE Trans. Aerosp. Electron. Syst., vol. 59, pp. 4159–4167, 2023, doi: 10.1109/TAES.2023.3237520.
K. Janocha and W. M. Czarnecki, “On loss functions for deep neural networks in classification,” arXiv preprint arXiv:1702.05659, 2017, doi: 10.4467/20838476SI.16.004.6185.
H. Rezatofighi et al., “Generalized Intersection over Union: A Metric and a Loss for Bounding Box Regression,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Long Beach, CA, USA, 2019, pp. 658– 666, doi: 10.1109/CVPR.2019.00075.
X. Li et al., “Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2020.
U. Ruby and V. Yendapalli, “Binary cross entropy with deep learning technique for image classification,” Int. J. Adv. Trends Comput. Sci. Eng., vol. 9, pp. 5393–5397, 2020, doi: 10.30534/ijatcse/2020/175942020.
Z. Zheng et al., “Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression,” in Proc. AAAI Conf. Artif. Intell. (AAAI), vol. 34, 2020, pp. 12993- 13000, doi: 10.1609/aaai.v34i07.6999.
C. Niu et al., “SAR-LtYOLOv8: A Lightweight YOLOv8 Model for Small Object Detection in SAR Ship Images,” Comput. Syst. Sci. Eng., vol. 48, pp. 827–845, 2024, doi: 10.32604/csse.2024.056736.
C. Guo, B. Fan, Q. Zhang, S. Xiang, and C. Pan, “AugFPN: Improving Multi-scale Feature Learning for Object Detection,” arXiv preprint arXiv:1912.05384, 2019, doi: 10.1109/CVPR42600.2020.01261.
Z. Zhang, X. Qiu, and Y. Li, “SEFPN: Scale-Equalizing Feature Pyramid Network for Object Detection,” Sensors, vol. 21, no. 21, Art. no. 7136, 2021, doi: 10.3390/s21217136.
H.-J. Park, J.-W. Kang, and B.-G. Kim, “ssFPN: Scale Sequence Feature-Based Feature Pyramid Network for Object Detection,” Sensors, vol. 23, no. 9, Art. no. 4432, 2023, doi: 10.3390/s23094432.
Y. Huang, D. Wang, B. Wu, and D. An, “NST-YOLO11: ViT Merged Model with Neuron Attention for Arbitrary-Oriented Ship Detection in SAR Images,” Remote Sens., vol. 16, Art. no. 4760, 2024, doi: 10.3390/rs 16244760.
C. Yu and Y. Shin, “SMEP-DETR: Transformer-Based Ship Detection for SAR Imagery with Multi-Edge Enhancement,” Remote Sens., vol. 17, 2025, doi: 10.3390/rs17060953.
Y. Xu, X. Xue, C. Li, S. Zhao, X. Xu, and C. Zeng, “RLE-YOLO: A Lightweight and Multiscale SAR Ship Detection Based on Improved YOLOv8,” IEEE Access, 2025, doi: 10.1109/ACCESS.2025.3550541.
J. Niu, M. Li, H. Lin, Y. Liu, Z. Liu, H. Li, and S. Niu, “LD-YOLO: A Lightweight Dynamic Convolution-Based YOLOv8n Framework for Robust Ship Detection in SAR Imagery,” IEEE Geosci. Remote Sens. Lett., vol. 23, pp. 1–5, 2026, doi: 10.1109/LGRS.2025.3630098.
X. Zhao et al., “Denoising-Enhanced YOLO for Robust SAR Ship Detection,” arXiv preprint arXiv:2602.23820, 2026.
Z. Yang, X. Xia, Y. Liu, G. Wen, W. E. Zhang, and L. Guo, “LPST-Det: Local-Perception-Enhanced Swin Transformer for SAR Ship Detection,” Remote Sens., vol. 16, no. 3, Art. no. 483, 2024, doi: 10.3390/rs16030483.