Balance Scene Learning Mechanism for Offshore and Inshore Ship Detection in SAR Images
arXiv:2007.10714v275 citations
AI Analysis
This work addresses a domain-specific problem for SAR image analysis, likely incremental as it focuses on balancing scene samples to improve detection.
The paper tackles the problem of reduced accuracy in SAR ship detection due to imbalanced sample numbers between offshore and inshore scenes, proposing a Balance Scene Learning Mechanism (BSLM) to address this issue.
Huge imbalance of different scenes' sample numbers seriously reduces Synthetic Aperture Radar (SAR) ship detection accuracy. Thus, to solve this problem, this letter proposes a Balance Scene Learning Mechanism (BSLM) for offshore and inshore ship detection in SAR images.