• Home
  • Search
  • RetinaNet-XAG: Multi-Category SAR Target Detection Under Sample Imbalance With Oriented Bounding Boxes
  • https://doi.org/10.1109/jstars.2025.3617483Copy DOI Icon

RetinaNet-XAG: Multi-Category SAR Target Detection Under Sample Imbalance With Oriented Bounding Boxes

  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Fine-grained classification of multi-category vehicles and ships in synthetic aperture radar (SAR) imagery and accurate orientation estimation remains challenging. This is mainly due to the imbalance among different classes, the lack of hard examples, and the presence of complex background clutter. Existing methods are often limited to single-class detection and demonstrate inadequate robustness in open-world scenarios. To address these limitations, a novel multi-category SAR object detection framework, RetinaNet-XAG, is proposed under multi-category sample-imbalanced conditions with oriented bounding boxes. The architecture incorporates a ConvNeXt backbone to enhance multi-scale feature representation and suppress background interference. An improved Adaptive Training Sample Selection strategy for Oriented bounding boxes (ATSSO) is introduced to balance positive and negative sample selection. Additionally, the Gaussian Wasserstein Distance (GWD) loss is adopted to improve regression accuracy for rotated bounding boxes. A Redundant Oriented Bounding Box Removal (ROR) module is further designed to eliminate conflicting multi-category predictions for single targets. To validate the proposed method under sample imbalance, a new benchmark dataset named the SAR-based Diverse Vehicle and Ship Dataset (SDVSD) is constructed, containing 19 categories sourced from multiple SAR platforms. Experimental results demonstrate that RetinaNet-XAG outperforms state-of-the-art methods in mean average precision (mAP), recall, and F1-score metrics, while exhibiting strong generalization capabilities in large-scale SAR application scenarios.

Similar Papers
  • PDF
  • Research Article
  • Citations14

Ship Classification in SAR Imagery by Shallow CNN Pre-Trained on Task-Specific Dataset with Feature Refinement

  • Nov 25, 2022
  • Remote Sensing
  • Haitao Lang +4
  • Research Article
  • Citations1

SAR-DRBNet: Adaptive Feature Weaving and Algebraically Equivalent Aggregation for High-Precision Rotated SAR Detection

  • Feb 16, 2026
  • Remote Sensing
  • Lanfang Lei +7
  • PDF
  • Research Article
  • Citations343

Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery

  • Mar 05, 2019
  • Remote Sensing
  • Yuanyuan Wang +4
  • Research Article
  • Citations2

Interpretation of Synthetic Aperture Radar (SAR) imagery for geological appraisal: A comparative study in Anantapur district of Andhra Pradesh

  • Dec 01, 1990
  • Journal of the Indian Society of Remote Sensing
  • S C Sharma +3
  • Conference Article
  • Citations4

Capability of geometric features to classify ships in SAR imagery

  • Oct 18, 2016
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Haitao Lang +3
  • Research Article
  • Citations1

WE-KAN: SAR Image Rotated Object Detection Method Based on Wavelet Domain Feature Enhancement and KAN Prediction Head.

  • Mar 24, 2026
  • Sensors (Basel, Switzerland)
  • Mingchun Li +3
  • PDF
  • Research Article
  • Citations10

An Anchor-Free Method Based on Adaptive Feature Encoding and Gaussian-Guided Sampling Optimization for Ship Detection in SAR Imagery

  • Apr 04, 2022
  • Remote Sensing
  • Bokun He +3
  • Research Article
  • Citations10

Dual-Modal Approach for Ship Detection: Fusing Synthetic Aperture Radar and Optical Satellite Imagery.

  • Jan 08, 2025
  • Sensors (Basel, Switzerland)
  • Mahmoud Ahmed +2
  • Research Article

The role of satellite image technology in maritime surveillance and national sovereignty using the Synthetic Aperture Radar (SAR) data approach

  • Mar 01, 2025
  • IOP Conference Series: Earth and Environmental Science
  • Rakha Asyrof +4
  • Book Chapter

Bootstrapping Stochastic Annealing EM Algorithm for Multiscale Segmentation of SAR Imagery

  • Jan 01, 2006
  • Xian-Bin Wen +2
  • Research Article
  • Citations1

YOSDet: A YOLO-Based Oriented Ship Detector in SAR Imagery

  • Feb 19, 2026
  • Remote Sensing
  • Chushi Yu +2
  • Research Article
  • Citations37

Multisource Heterogeneous Transfer Learning via Feature Augmentation for Ship Classification in SAR Imagery

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Haitao Lang +3
  • Research Article

Semantic-Anchored Cross-Modal Distillation Framework With Foundation Models for SAR Ship Recognition

  • Jan 01, 2025
  • IEEE Transactions on Aerospace and Electronic Systems
  • Xuemeng Hui +3
  • Conference Article
  • Citations7

Ship Detection Based on Faster R-CNN in SAR Imagery by Anchor Box Optimization

  • Oct 01, 2019
  • Durga Kumar +1
  • Research Article
  • Citations8

Fast algorithm for maneuvering target detection in SAR imagery based on gridding and fusion of texture features

  • Jan 01, 2011
  • Geo-spatial Information Science
  • Zhan Yuan +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.