Wavelet-Guided Token-Focus Transformer for Fine-Grained Ship Recognition
IEEE Signal Processing Letters · 2026 · 33 · 1896-1900
DOI: 10.1109/lsp.2026.3687795 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Runtian Wang und 2 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Fine-grained ship recognition in complex backgrounds is challenged by significant texture variations and the frequent occlusion of the ship's core structure by noise. Existing studies have not effectively addressed complex background interference and lack the ability to dynamically focus on the most discriminative features, particularly in small target recognition tasks. To overcome these issues, this paper proposes a novel end-to-end network architecture that integrates Multi-Scale Wavelet Block (MSWB) and Token Focus Attention Block (TFAB), which effectively focuses on key ship features while mitigating the impact of background noise. The proposed method is evaluated on the constructed Complex Background Ships (GCS) dataset, as well as the publicly available MAR-ships and Game-of-Ships datasets. Experimental results demonstrate that our method achieves leading accuracy of 85.7%, 95.7%, and 98.1% on these three datasets, respectively. The method significantly enhances the robustness and precision of ship recognition in real-world scenarios and provides valuable insights for dynamic monitoring applications.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wang, R., Qiao, R., & Cai, C. (2026). Wavelet-Guided Token-Focus Transformer for Fine-Grained Ship Recognition. IEEE Signal Processing Letters, 33, 1896-1900. https://doi.org/10.1109/lsp.2026.3687795
Vancouver
Wang R, Qiao R, Cai C. Wavelet-Guided Token-Focus Transformer for Fine-Grained Ship Recognition. IEEE Signal Processing Letters. 2026;33:1896-1900. doi:10.1109/lsp.2026.3687795
BibTeX
@article{Wang2026,
author = {Wang, Runtian and Qiao, Renjie and Cai, Chengtao},
title = {Wavelet-Guided Token-Focus Transformer for Fine-Grained Ship Recognition},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {1896--1900},
doi = {10.1109/lsp.2026.3687795}
}
EUVIMED