EUVIMEDEUVIMED entdecken
Crossref

Knowledge-inspired and sample-generation-based spectral augmentation for few-shot underwater acoustic target recognition

Wei Gao iD, Desheng Chen, Junhui Zhang, Xianda Zhang, Yining Liu iD

The Journal of the Acoustical Society of America · 01.07.2026 · 160 (1) · 603-618

DOI: 10.1121/10.0044413 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 16.07.2026. Verfasst von Wei Gao und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China. Die Arbeit nennt 35 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Innovative Research Group Project of the National Natural Science Foundation of China, Southern Marine Science and Engineering Guangdong Laboratory.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges of data scarcity and non-stationary noise interference in underwater acoustic target recognition in complex marine environments, existing few-shot learning methods often lack effective mechanisms to exploit structured spectrotemporal characteristics under low-signal-to-noise ratio conditions. This paper proposes a sample-generation-based few-shot underwater acoustic target recognition framework with a knowledge-inspired spectral decomposition augmentation strategy and a cross-feature guided recalibration module. The spectral decomposition augmentation module operates in the spatial-frequency domain of spectrograms to construct complementary multi-view samples by preserving coarse spectrotemporal structures while suppressing noise-sensitive fine texture variations. A Siamese network with time-frequency attention is employed to learn robust spectrotemporal representations, while the cross-feature guided recalibration module uses original-view features to perform dynamic gated recalibration on augmented views, thereby reducing sensitivity to noise-induced variations. Multi-view joint learning based on cosine similarity encourages the learning of shared discriminative representations across views. In addition, a task-adaptive fine-tuning mechanism with pseudo-sample generation is introduced to improve adaptation to novel classes. Experimental results on the ShipsEar dataset and the cross-domain DanShip dataset demonstrate that the proposed method achieves superior recognition accuracy and robustness under low-signal-to-noise ratio and cross-domain conditions compared with existing state-of-the-art few-shot learning methods.

Autor:innen und Institutionen

  • School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China.
  • School of Ocean Engineering and Technology, Sun Yat-sen University, and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519000, China.
  • Hanjiang National Laboratory, Zhuhai 519000, China.
  • Guangdong Provincial Key Laboratory of Information Technology for Deep Water Acoustics, Zhuhai 519000, China.

ORCID-Profile: Wei Gao, Yining Liu

Förderung

  • National Natural Science Foundation of China
  • Innovative Research Group Project of the National Natural Science Foundation of China
  • Southern Marine Science and Engineering Guangdong Laboratory

Zitieren

APA

Gao, W., Chen, D., Zhang, J., Zhang, X., & Liu, Y. (2026). Knowledge-inspired and sample-generation-based spectral augmentation for few-shot underwater acoustic target recognition. The Journal of the Acoustical Society of America, 160(1), 603-618. https://doi.org/10.1121/10.0044413

Vancouver

Gao W, Chen D, Zhang J, Zhang X, Liu Y. Knowledge-inspired and sample-generation-based spectral augmentation for few-shot underwater acoustic target recognition. The Journal of the Acoustical Society of America. 2026;160(1):603-618. doi:10.1121/10.0044413

BibTeX
@article{Gao2026,
  author = {Gao, Wei and Chen, Desheng and Zhang, Junhui and Zhang, Xianda and Liu, Yining},
  title = {Knowledge-inspired and sample-generation-based spectral augmentation for few-shot underwater acoustic target recognition},
  journal = {The Journal of the Acoustical Society of America},
  year = {2026},
  volume = {160},
  number = {1},
  pages = {603--618},
  doi = {10.1121/10.0044413}
}
Kostenlos starten →