EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

YOLO Variant Evaluation and Transfer Learning Analysis for Side-Scan Sonar Object Detection

Lei Liu, Houpu Li, Junhui Zhu, Ye Peng, Guojun Zhai

Journal of Marine Science and Engineering · 15.03.2026 · 14 (6) · 550

DOI: 10.3390/jmse14060550 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 15.03.2026. Verfasst von Lei Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Side-scan sonar is essential to underwater target detection, yet its effectiveness is hindered by scarce annotated data and complex acoustic artifacts. This study systematically evaluates four YOLO variants, YOLOv8n, YOLOv10n, YOLOv11n, and the newly released YOLOv13n, on two public side-scan sonar datasets with limited samples and severe class imbalance. We assess detection accuracy, computational efficiency, inference speed, and transfer learning using COCO pre-trained weights, as well as the impact of optimizer choice between SGD and AdamW. The results reveal distinct strengths: YOLOv8n achieves the fastest inference at 60.98 FPS, with a competitive mAP50 of 0.906, ideal for real-time applications. YOLOv11n offers the best accuracy–efficiency balance, attaining the highest recall of 0.859 and mAP50 of 0.917. YOLOv13n demonstrates exceptional precision of 0.993 and high-IoU localization, with an mAP75 of 0.760. Transfer learning consistently boosts performance, with average mAP50:95 gains exceeding 54% on the more challenging dataset, highlighting its critical role in overcoming data scarcity. SGD generally outperforms AdamW, confirming its suitability as the default optimizer. These findings provide practical guidelines: YOLOv8 for real-time needs, YOLOv11 for balanced performance, and YOLOv13 for precision-critical tasks with ample resources. This work also establishes a benchmark for future underwater autonomous system research.

Förderung

  • the National Natural Science Foundation of China

Zitieren

APA

Liu, L., Li, H., Zhu, J., Peng, Y., & Zhai, G. (2026). YOLO Variant Evaluation and Transfer Learning Analysis for Side-Scan Sonar Object Detection. Journal of Marine Science and Engineering, 14(6), 550. https://doi.org/10.3390/jmse14060550

Vancouver

Liu L, Li H, Zhu J, Peng Y, Zhai G. YOLO Variant Evaluation and Transfer Learning Analysis for Side-Scan Sonar Object Detection. Journal of Marine Science and Engineering. 2026;14(6):550. doi:10.3390/jmse14060550

BibTeX
@article{Liu2026,
  author = {Liu, Lei and Li, Houpu and Zhu, Junhui and Peng, Ye and Zhai, Guojun},
  title = {YOLO Variant Evaluation and Transfer Learning Analysis for Side-Scan Sonar Object Detection},
  journal = {Journal of Marine Science and Engineering},
  year = {2026},
  volume = {14},
  number = {6},
  pages = {550},
  doi = {10.3390/jmse14060550}
}
Kostenlos starten →