EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient YOLOv11 with a FasterNet Backbone and Attention for Multi-Class Underwater Object Detection in Nearshore Waters

Yinghao He, Wenjie Yin, Ruomiao Song, Siyi Zhou, Shimin Shan, Shuo Liu

Journal of Marine Science and Engineering · 29.04.2026 · 14 (9) · 827

DOI: 10.3390/jmse14090827 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 29.04.2026. Verfasst von Yinghao He und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Educational Department of Liaoning Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Underwater multi-class object detection in nearshore waters is essential for intelligent cleaning operations and ecological monitoring. However, strong reflection and scattering interference, color attenuation, frequent occlusion, and non-rigid deformation often cause fine-grained information loss and feature misalignment in conventional detectors, leading to missed and false detections. To address these challenges, we propose an enhanced YOLOv11 framework integrating FasterNet and attention mechanisms. Specifically, we include FasterNet to replace the YOLOv11 baseline backbone to improve fine-grained feature preservation while reducing computational redundancy. Furthermore, a Deformable Underwater Attention Module (DUAM) is introduced to capture local texture variations and deformation-aware features, enhancing discrimination among heterogeneous categories. Additionally, a Submerged Occlusion-Aware Head (SOAH) is designed to recalibrate features based on occlusion visibility, improving the detection of small-scale and partially occluded objects in the high-resolution P2 layer. Performance gains mainly stem from the recalibration strategy and its synergy with multi-scale optimization objectives. Experiments on a nearshore underwater multi-class dataset (8610 images across 40 classes) show that the proposed method increases mAP from 66.9% to 82.3%, achieving a 15.4-point improvement over baseline YOLOv11, with superior robustness under complex backgrounds.

Förderung

  • Educational Department of Liaoning Province

Zitieren

APA

He, Y., Yin, W., Song, R., Zhou, S., Shan, S., & Liu, S. (2026). Efficient YOLOv11 with a FasterNet Backbone and Attention for Multi-Class Underwater Object Detection in Nearshore Waters. Journal of Marine Science and Engineering, 14(9), 827. https://doi.org/10.3390/jmse14090827

Vancouver

He Y, Yin W, Song R, Zhou S, Shan S, Liu S. Efficient YOLOv11 with a FasterNet Backbone and Attention for Multi-Class Underwater Object Detection in Nearshore Waters. Journal of Marine Science and Engineering. 2026;14(9):827. doi:10.3390/jmse14090827

BibTeX
@article{He2026,
  author = {He, Yinghao and Yin, Wenjie and Song, Ruomiao and Zhou, Siyi and Shan, Shimin and Liu, Shuo},
  title = {Efficient YOLOv11 with a FasterNet Backbone and Attention for Multi-Class Underwater Object Detection in Nearshore Waters},
  journal = {Journal of Marine Science and Engineering},
  year = {2026},
  volume = {14},
  number = {9},
  pages = {827},
  doi = {10.3390/jmse14090827}
}
Kostenlos starten →