A Lightweight Framework With Pruning and Knowledge Distillation for Ship Detection in SAR Images
Open Access
- 6 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 13220-13233
Abstract
Lightweight synthetic aperture radar (SAR) ship detection is critical for real-time maritime monitoring on resource-constrained platforms. However, speckle noise and sea clutter often obscure small and low-contrast vessels, making accurate detection difficult under strict computational budgets. To address this, we propose a compact detection framework that integrates layerwise amplitude-based pruning with dual-stream knowledge distillation, enabling substantial model compression while maintaining detection performance. In addition, we adopt efficiency-oriented building blocks to improve feature utilization and introduce a localization-aware regression objective to strengthen bounding box fitting on low intersection over union (IoU) samples. Experiments on three public SAR ship detection benchmarks demonstrate that the proposed pruned and distilled model achieves higher precision and mean average precision (mAP) than recent peer methods, while running above 200 frames per second (FPS) with only 7.4 M parameters and 41.9 G floating point operations (FLOPs). These results indicate that pruning-guided distillation provides an effective and practical path toward deployable SAR ship detection.Keywords
Funding Information
- China Association for Science and Technology
- Youth Talent Support Program
- Princess Nourah Bint Abdulrahman University
- Princess Nourah bint Abdulrahman University Researchers Supporting Project (PNURSP2026R440)
This publication has 52 references indexed in Scilit:
- Crack segmentation and quantification in concrete structures using a lightweight YOLO model based on pruning and knowledge distillationExpert Systems with Applications, 2025
- TPS-YOLO: The Efficient Tiny Person Detection Network Based on Improved YOLOv8 and Model Pruning2025
- Dualswin-Ynet: A Novel Bimodal Fusion Network for Ship Detection in Remote Sensing Images2024
- Embedded YOLO v8: Real-time detection of sugarcane nodes in complex natural environments by rapid structural pruning methodMeasurement, 2024
- A Review on YOLOv8 and Its Advancements2024
- DD‐YOLO: An object detection method combining knowledge distillation and Differentiable Architecture SearchIET Computer Vision, 2022
- Real-time defects detection for apple sorting using NIR cameras with pruning-based YOLOV4 networkComputers and Electronics in Agriculture, 2022
- Pruned-YOLO: Learning Efficient Object Detector Using Model Pruning2021
- A CenterNet++ model for ship detection in SAR imagesPattern Recognition, 2021
- HRSID: A High-Resolution SAR Images Dataset for Ship Detection and Instance SegmentationIEEE Access, 2020