Hybrid local-global representation learning with stochastic Gaussian classification for underwater acoustic target recognition
Cheng Yang, Qisheng Xu, Ming Feng, Hui Yang, Yulei Yuan, Yutao Dou, Junyi Zhao, Kele Xu · 2025
Read Hybrid local-global representation learning with stochastic Gaussian classification for underwater acoustic target recognition by Cheng Yang, Qisheng Xu, Ming Feng, Hui Yang, Yulei Yuan, Yutao Dou, Junyi Zhao, Kele Xu (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12816598.txt.
Description
Cheng Yang and co-authors build a listener for underwater targets in a 2025 paper. Picking out ships and other targets from sea sound is hard: water bends sound, noise is high, and conditions shift fast. A firm call near class borders adds strain.
Their frame joins two ears: a pre-trained sound transformer for long-range patterns, and a multi-scale filter net for fine local marks. A final step samples class weights from bell curves to steady borderline calls. Tests on two standard sets gave top scores and held up under added noise. Part-removal tests back each piece of the design.
Catalog record
| CREATOR | Cheng Yang, Qisheng Xu, Ming Feng, Hui Yang, Yulei Yuan, Yutao Dou, Junyi Zhao, Kele Xu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 113 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |