A few-shot learning method for underwater acoustic target recognition based on generative data augmentation
The Journal of the Acoustical Society of America · 01.05.2026 · 159 (5) · 3773-3791
DOI: 10.1121/10.0043727 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 01.05.2026. Verfasst von Wei Huang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Information Science and Engineering, Ocean University of China, Qingdao, Shandong 266100, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province, Key Technologies Research and Development Program.
Abstract (Originalsprache)
The recognition of underwater acoustic targets (UATR) is of great significance for the protection of marine diversity and national defense security. The development of deep learning provides new opportunities for UATR, but faces challenges brought by the scarcity of reference samples and complex environmental interference. To tackle this problem, we propose a generative discriminative collaborative framework, a variational auto-encoder boosted learning framework based on latent space completion. Rooted in the core contradiction arising from the incompleteness of intra-class manifolds and the instability of discriminative boundaries, this framework incorporates the premise of latent space continuity. Leveraging a structure-preserving generative reconstruction mechanism, it implicitly supplements the original dataset, which in turn enables the reconstruction of intra-class distributions that are more continuous, integral, and discriminative at the feature level. In this paper, we construct a three-stage pipeline system consisting of auto-clean cut unified preprocessing, latent reconstruction variational auto-encoder multi-scale latent space reconstruction, and an acoustic identification model. Furthermore, by establishing a staged modeling workflow, data purification, latent space completion, and discriminative optimization converge on their individual objectives independently while maintaining overall synergy, thus forging a robust recognition paradigm tailored to few-shot learning scenarios.
Autor:innen und Institutionen
- Faculty of Information Science and Engineering, Ocean University of China, Qingdao, Shandong 266100, China.
- School of Space Science and Engineering, Shandong University at Weihai, Weihai, Shandong 264200, China.
ORCID-Profile: Wei Huang
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong Province
- Key Technologies Research and Development Program
- Fundamental Research Funds for the Central Universities, Ocean University of China
Zitieren
APA
Huang, W., Zhang, Q., Zhao, B., Xu, T., & Zhang, H. (2026). A few-shot learning method for underwater acoustic target recognition based on generative data augmentation. The Journal of the Acoustical Society of America, 159(5), 3773-3791. https://doi.org/10.1121/10.0043727
Vancouver
Huang W, Zhang Q, Zhao B, Xu T, Zhang H. A few-shot learning method for underwater acoustic target recognition based on generative data augmentation. The Journal of the Acoustical Society of America. 2026;159(5):3773-3791. doi:10.1121/10.0043727
BibTeX
@article{Huang2026,
author = {Huang, Wei and Zhang, Qirui and Zhao, Bowen and Xu, Tianhe and Zhang, Hao},
title = {A few-shot learning method for underwater acoustic target recognition based on generative data augmentation},
journal = {The Journal of the Acoustical Society of America},
year = {2026},
volume = {159},
number = {5},
pages = {3773--3791},
doi = {10.1121/10.0043727}
}
EUVIMED