Leveraging Prior Knowledge in Semi-Supervised Learning for Precise Target Recognition
Remote Sensing · 08.07.2025 · 17 (14) · 2338
DOI: 10.3390/rs17142338 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 08.07.2025. Verfasst von Guohao Xie und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangxi Special Program for Technological Innovation Guidance, Guangxi Natural Science Foundation.
Abstract (Originalsprache)
Underwater acoustic target recognition (UATR) is challenged by complex marine noise, scarce labeled data, and inadequate multi-scale feature extraction in conventional methods. This study proposes DART-MT, a semi-supervised framework that integrates a Dual Attention Parallel Residual Network Transformer with a mean teacher paradigm, enhanced by domain-specific prior knowledge. The architecture employs a Convolutional Block Attention Module (CBAM) for localized feature refinement, a lightweight New Transformer Encoder for global context modeling, and a novel TriFusion Block to synergize spectral–temporal–spatial features through parallel multi-branch fusion, addressing the limitations of single-modality extraction. Leveraging the mean teacher framework, DART-MT optimizes consistency regularization to exploit unlabeled data, effectively mitigating class imbalance and annotation scarcity. Evaluations on the DeepShip and ShipsEar datasets demonstrate state-of-the-art accuracy: with 10% labeled data, DART-MT achieves 96.20% (DeepShip) and 94.86% (ShipsEar), surpassing baseline models by 7.2–9.8% in low-data regimes, while reaching 98.80% (DeepShip) and 98.85% (ShipsEar) with 90% labeled data. Under varying noise conditions (−20 dB to 20 dB), the model maintained a robust performance (F1-score: 92.4–97.1%) with 40% lower variance than its competitors, and ablation studies validated each module’s contribution (TriFusion Block alone improved accuracy by 6.9%). This research advances UATR by (1) resolving multi-scale feature fusion bottlenecks, (2) demonstrating the efficacy of semi-supervised learning in marine acoustics, and (3) providing an open-source implementation for reproducibility. In future work, we will extend cross-domain adaptation to diverse oceanic environments.
Förderung
- Guangxi Special Program for Technological Innovation Guidance
- Guangxi Natural Science Foundation
Zitieren
APA
Xie, G., Chen, Z., Li, Y., Chen, M., Chen, F., Zhang, Y., Jiang, H., & Qiu, H. (2025). Leveraging Prior Knowledge in Semi-Supervised Learning for Precise Target Recognition. Remote Sensing, 17(14), 2338. https://doi.org/10.3390/rs17142338
Vancouver
Xie G, Chen Z, Li Y, Chen M, Chen F, Zhang Y, et al. Leveraging Prior Knowledge in Semi-Supervised Learning for Precise Target Recognition. Remote Sensing. 2025;17(14):2338. doi:10.3390/rs17142338
BibTeX
@article{Xie2025,
author = {Xie, Guohao and Chen, Zhe and Li, Yaan and Chen, Mingsong and Chen, Feng and Zhang, Yuxin and Jiang, Hongyan and Qiu, Hongbing},
title = {Leveraging Prior Knowledge in Semi-Supervised Learning for Precise Target Recognition},
journal = {Remote Sensing},
year = {2025},
volume = {17},
number = {14},
pages = {2338},
doi = {10.3390/rs17142338}
}
EUVIMED