SPyramidLightNet: A Lightweight Shared Pyramid Network for Efficient Underwater Debris Detection
Source abstract
Abstract
Underwater debris detection plays a crucial role in marine environmental protection. However, existing object detection algorithms generally suffer from excessive model complexity and insufficient detection accuracy, making it difficult to meet the real-time detection requirements in resource-constrained underwater environments. To address this challenge, this paper proposes a novel lightweight object detection network named the Shared Pyramid Lightweight Network (SPyramidLightNet). The network adopts an improved architecture based on YOLOv11 and achieves an optimal balance between detection performance and computational efficiency by integrating three core innovative modules. First, the Split–Merge Attention Block (SMAB) employs a dynamic kernel selection mechanism and split–merge strategy, significantly enhancing feature representation capability through adaptive multi-scale feature fusion. Second, the C3 GroupNorm Detection Head (C3GNHead) introduces a shared convolution mechanism and GroupNorm normalization strategy, substantially reducing the computational complexity of the detection head while maintaining detection accuracy. Finally, the Shared Pyramid Convolution (SPyramidConv) replaces traditional pooling operations with a parameter-sharing multi-dilation-rate convolution architecture, achieving more refined and efficient multi-scale feature aggregation. Extensive experiments on underwater debris datasets demonstrate that SPyramidLightNet achieves 0.416 on the mAP@0.5:0.95 metric, significantly outperforming mainstream algorithms including Faster-RCNN, SSD, RT-DETR, and the YOLO series. Meanwhile, compared to the baseline YOLOv11, the proposed algorithm achieves an 11.8% parameter compression and a 17.5% computational complexity reduction, with an inference speed reaching 384 FPS, meeting the stringent requirements for real-time detection. Ablation experiments and visualization analyses further validate the effectiveness and synergistic effects of each core module. This research provides important theoretical guidance for the design of lightweight object detection algorithms and lays a solid foundation for the development of automated underwater debris recognition and removal technologies.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Underwater Acoustics Research · Underwater Vehicles and Communication Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Water and Environmental Engineering Laboratory, Interdisciplinary Graduate School of Engineering Sciences, Kyushu University, 6-1 Kasuga-Koen, Kasuga 816-8580, Fukuoka, Japan
References (58)
Show source-provided references
1. Plastic waste inputs from land into the ocean10.1126/science.1260352 ↗
2. The deep sea is a major sink for microplastic debris10.1098/rsos.140317 ↗
3. The physical impacts of microplastics on marine organisms: A review10.1016/j.envpol.2013.02.031 ↗
4. Fulton, M., Hong, J., Islam, M.J., and Sattar, J. (2019, January 20–24). Robotic detection of marine litter using deep visual detection models. Proceedings of the IEEE International Conference on Robotics and Automation 2019, Montreal, QC, Canada.10.1109/ICRA.2019.8793975 ↗
5. Real-time underwater object detection technology for complex underwater environments based on deep learning
6. Er, M.J., Chen, J., Zhang, Y., and Gao, W. (2023). Research challenges, recent advances, and popular datasets in deep learning-based underwater marine object detection: A review. Sensors, 23.10.36227/techrxiv.19350389.v4 ↗
7. A systematic review and analysis of deep learning-based underwater object detection10.1016/j.neucom.2023.01.056 ↗
8. Akkaynak, D., and Treibitz, T. (2019, January 15–20). Sea-thru: A method for removing water from underwater images. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00178 ↗
9. Underwater image enhancement using polarimetric filtering
10. Islam, M.J., Edge, C., Xiao, Y., Luo, P., Ahmed, M., Morse, C., and Sattar, J. (2020–24, January 24). Semantic segmentation of underwater imagery: Dataset and benchmark. Proceedings of the 2020 IEEE/CVF International Conference on Computer Vision, Las Vegas, NV, USA.10.1109/IROS45743.2020.9340821 ↗
11. Fan, Y., Liu, J., Zhang, M., and Wang, L. (2024). A small underwater object detection model with enhanced feature extraction and fusion. Sci. Rep., 15.10.1038/s41598-025-85961-9 ↗
12. Autonomous underwater vehicle trajectory planning for real-time photogrammetric survey
13. Moniruzzaman, M., Islam, S.M.S., Bennamoun, M., and Lavery, P. (2017). Deep learning on underwater marine object detection: A survey. Advanced Concepts for Intelligent Vision Systems, Springer.10.1007/978-3-319-70353-4_13 ↗
14. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
15. A deep learning framework based on structured space model for detecting small objects in complex underwater environments
16. YOLO-UOD: An underwater small object detector via improved efficient layer aggregation network10.1049/ipr2.13112 ↗
17. CEH-YOLO: A composite enhanced YOLO-based model for underwater object detection10.1016/j.ecoinf.2024.102758 ↗
18. Lightweight deep neural network for joint learning of underwater object detection and color conversion10.1109/TNNLS.2021.3072414 ↗
19. A comprehensive review of model compression techniques in machine learning
20. Learning both weights and connections for efficient neural networks
21. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
22. Underwater small object detection via automatic encoding pyramid with neighborhood information
23. A survey of model compression strategies for object detection
24. Deep learning for generic object detection: A survey
25. Chen, Y., Liu, S., Wang, H., Zhang, M., and Li, J. (2024). Optimizing Edge AI: A comprehensive survey on data, model, and system strategies. arXiv.
26. Efficient neural networks for edge devices
27. A comprehensive survey of deep learning-based lightweight object detection models for edge devices10.1007/s10462-024-10877-1 ↗
28. Lightweight Deep Learning for Resource-Constrained Environments: A Survey
29. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., and Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv.
30. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18–23). MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
31. Tan, M., and Le, Q. (2019, January 9–15). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 2019 International Conference on Machine Learning, Long Beach, CA, USA.
32. Koonce, B. (2021). MobileNetV3. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, Apress.10.1007/978-1-4842-6168-2 ↗
33. Zhang, X., Zhou, X., and Lin, M. (2018, January 18–23). Shufflenet: An extremely efficient convolutional neural network for mobile devices. Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00716 ↗
34. Ma, N., Zhang, X., and Zheng, H.T. (2018, January 8–14). Shufflenet v2: Practical guidelines for efficient cnn architecture design. Proceedings of the 2018 Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01264-9_8 ↗
35. Koonce, B. (2021). EfficientNet. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, Apress.10.1007/978-1-4842-6168-2 ↗
36. Tan, M., and Le, Q. (2019, January 9–15). Efficientnetv2: Smaller models and faster training. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA. PMLR, 2021.
37. Fan, B., Chen, Y., Qu, J., Chai, Y., Xiao, C., and Huang, P. (2019, January 22–25). FFBNet: Lightweight backbone for object detection based feature fusion block. Proceedings of the IEEE International Conference on Image Processing, Taipei, Taiwan.10.1109/ICIP.2019.8803683 ↗
38. Liu, W., Liao, S., Ren, W., Hu, W., and Yu, Y. (2019, January 15–20). High-level semantic feature detection: A new perspective for pedestrian detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00533 ↗
39. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, faster, stronger. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
40. Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2023, January 17–24). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00721 ↗
41. Yolov10: Real-time end-to-end object detection
42. Liu, W., Anguelov, D., and Erhan, D. (2016, January 11–14). Ssd: Single shot multibox detector. Proceedings of the Computer Vision—ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Proceedings, Part I 14.
43. Xiong, Y., Liu, H., and Gupta, S. (2021, January 20–25). Mobiledets: Searching for object detection architectures for mobile accelerators. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00382 ↗
44. Lin, T.Y., Goyal, P., and Girshick, R. (2017, January 22–29). Focal loss for dense object detection. Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.324 ↗
45. Lin, T.Y., Dollár, P., and Girshick, R. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
46. Liu, S., Qi, L., and Qin, H. (2018, January 18–23). Path aggregation network for instance segmentation. Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00913 ↗
47. Chen, J., Mai, H.S., and Luo, L. (2021, January 19–22). Effective feature fusion network in BIFPN for small object detection. Proceedings of the 2021 IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA.10.1109/ICIP42928.2021.9506347 ↗
48. An anchor-free object detector based on soften optimized bi-directional FPN10.1016/j.cviu.2022.103410 ↗
49. Underwater image enhancement by dehazing with minimum information loss and histogram distribution prior10.1109/TIP.2016.2612882 ↗
50. Drews, P., Nascimento, E., Moraes, F., Botelho, S., and Campos, M. (2013, January 2–8). Transmission estimation in underwater single images. Proceedings of the IEEE International Conference on Computer Vision Workshops 2013, Sydney, Australia.10.1109/ICCVW.2013.113 ↗
51. FW-GAN: Underwater image enhancement using generative adversarial network with multi-scale fusion10.1016/j.image.2022.116855 ↗
52. Yin, X., Chen, X., and Yang, Y. (2023). Underwater Image Enhancement Algorithm Based on UWGAN and U-Net. Advances in Machinery, Materials Science and Engineering Application IX, IOS Press.10.3233/ATDE230554 ↗
53. Li, C., Yu, D., and Li, H. (2024). Underwater Image Enhancement Method Based on MuLA-GAN. Annual Conference of China Electrotechnical Society, Springer Nature.10.1007/978-981-96-0897-3_51 ↗
54. Chen, Y., Li, H., and Yuan, Q. (2023, January 24–26). Underwater Image Enhancement based on Improved Water-Net. Proceedings of the 2022 IEEE International Conference on Cyborg and Bionic Systems (CBS), Wuhan, China.10.1109/CBS55922.2023.10115390 ↗
55. Li, Z., Zheng, B., and Chao, D. (2024). Underwater-Yolo: Underwater Object Detection Network with Dilated Deformable Convolutions and Dual-Branch Occlusion Attention Mechanism. J. Mar. Sci. Eng., 12.10.3390/jmse12122291 ↗
56. Chen, L., Yang, Y., and Wang, Z. (2023). Underwater target detection lightweight algorithm based on multi-scale feature fusion. J. Mar. Sci. Eng., 11.10.3390/jmse11020320 ↗
57. Yang, H.H., Huang, K.C., and Chen, W.T. (June, January 30). Laffnet: A lightweight adaptive feature fusion network for underwater image enhancement. In Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi’an, China.10.1109/ICRA48506.2021.9561263 ↗
58. Gong, T., Zhang, M., and Zhou, Y. (2023). Underwater image enhancement based on color feature fusion. Electronics, 12.10.3390/electronics12244999 ↗