DACF-net: a dynamic attention and context fusion network with geometry-aware multi-scale refinement for sar ship instance segmentation
Open Access
- 8 September 2026
- journal article
- research article
- Published by Taylor & Francis in International Journal of Digital Earth
- Vol. 19 (2)
Abstract
1. Synthetic aperture radar (SAR) is a key remote sensing technology that actively transmits microwave pulses and receives echoes for Earth observation. With all-weather and all-day imaging capabil...Keywords
Funding Information
- National Key Research and Development Program of China (2024YFB3908600)
- Guided Project of Hubei Provincial Department of Education (B2023246)
- Science and Technology Project of Hubei Provincial Department of Transportation (2024-81-3-3)
- Key Research and Development Project of Hubei Province (2023BCA003, 2024BCB101)
This publication has 54 references indexed in Scilit:
- Glance-Focus-Gaze: A novel Eagle-Eye Vision-Inspired Panorama-Population-Individual progressive screening paradigm to capture ships in SAR imagesISPRS Journal of Photogrammetry and Remote Sensing, 2026
- MBLKNet: a large kernel convolution-driven network with multi-task self-supervised learning for SAR maritime target classificationGeo-spatial Information Science, 2025
- YOLOShipTracker: Tracking ships in SAR images using lightweight YOLOv8International Journal of Applied Earth Observation and Geoinformation, 2024
- NRENet: Neighborhood removal-and-emphasis network for ship detection in SAR ImagesInternational Journal of Applied Earth Observation and Geoinformation, 2024
- SAR ship detection based on salience region extraction and multi-branch attentionInternational Journal of Applied Earth Observation and Geoinformation, 2023
- HRSID: A High-Resolution SAR Images Dataset for Ship Detection and Instance SegmentationIEEE Access, 2020
- Libra R-CNN: Towards Balanced Learning for Object Detection2019
- Ship detection in SAR images based on an improved faster R-CNN2017
- Feature Pyramid Networks for Object Detection2017
- Going deeper with convolutions2015