Unsupervised Domain-Adaptive SAR Ship Detection Based on Cross-Domain Feature Interaction and Data Contribution Balance
Remote Sensing · 21.01.2024 · 16 (2) · 420
DOI: 10.3390/rs16020420 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 21.01.2024. Verfasst von Yanrui Yang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Anhui Province, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
Due to the complex imaging mechanism of SAR images and the lack of multi-angle and multi-parameter real scene SAR target data, the generalization performance of existing deep-learning-based synthetic aperture radar (SAR) image target detection methods are extremely limited. In this paper, we propose an unsupervised domain-adaptive SAR ship detection method based on cross-domain feature interaction and data contribution balance. First, we designed a new cross-domain image generation module called CycleGAN-SCA to narrow the gap between the source domain and the target domain. Second, to alleviate the influence of complex backgrounds on ship detection, a new backbone using a self-attention mechanism to tap the potential of feature representation was designed. Furthermore, aiming at the problems of low resolution, few features and easy information loss of small ships, a new lightweight feature fusion and feature enhancement neck was designed. Finally, to balance the influence of different quality samples on the model, a simple and efficient E12IoU Loss was constructed. Experimental results based on a self-built large-scale optical-SAR cross-domain target detection dataset show that compared with existing cross-domain methods, our method achieved optimal performance, with the mAP reaching 68.54%. Furthermore, our method achieved a 6.27% improvement compared to the baseline, even with only 5% of the target domain labeled data.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Anhui Province
- China Postdoctoral Science Foundation
Zitieren
APA
Yang, Y., Chen, J., Sun, L., Zhou, Z., Huang, Z., & Wu, B. (2024). Unsupervised Domain-Adaptive SAR Ship Detection Based on Cross-Domain Feature Interaction and Data Contribution Balance. Remote Sensing, 16(2), 420. https://doi.org/10.3390/rs16020420
Vancouver
Yang Y, Chen J, Sun L, Zhou Z, Huang Z, Wu B. Unsupervised Domain-Adaptive SAR Ship Detection Based on Cross-Domain Feature Interaction and Data Contribution Balance. Remote Sensing. 2024;16(2):420. doi:10.3390/rs16020420
BibTeX
@article{Yang2024,
author = {Yang, Yanrui and Chen, Jie and Sun, Long and Zhou, Zheng and Huang, Zhixiang and Wu, Bocai},
title = {Unsupervised Domain-Adaptive SAR Ship Detection Based on Cross-Domain Feature Interaction and Data Contribution Balance},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {2},
pages = {420},
doi = {10.3390/rs16020420}
}
EUVIMED