• Home
  • Search
  • Unsupervised Domain Adaptation Based on Progressive Transfer for Ship Detection: From Optical to SAR Images
  • Cite Icon72
  • https://doi.org/10.1109/tgrs.2022.3185298Copy DOI Icon

Unsupervised Domain Adaptation Based on Progressive Transfer for Ship Detection: From Optical to SAR Images

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In recent years, Synthetic Aperture Radar (SAR) ship detection methods based on convolutional neural networks have attracted wide attention in remote sensing fields. However, these methods require a large number of labeled SAR images to train the network, where labeling for SAR images is more expensive and time-consuming than that for optical images. To address the problem of lacking labeled SAR images, in this paper, we proposed an unsupervised domain adaptation framework based on progressive transfer for SAR ship detection by transferring knowledge from the optical domain to the SAR domain. Due to the prominent difference between the optical and SAR images, our approach progressively transfers knowledge from three levels: pixel level, feature level and prediction level. At the pixel level, considering the difference in imaging mechanism, we propose a special data augmentation method for ship targets and build the generator with skip-connection based on generative adversarial networks (GANs) to generate transition domain, which can reduce the appearance discrepancy between the optical and SAR images. At the feature level, the detector is trained to learn the domain-invariant features with adversarial alignment. At the prediction level, we further use the predicted pseudo-labels obtained by the feature-aligned detector to learn more discriminative features of the SAR images directly and propose the robust self-training (RST) method to reduce the influence of noisy pseudo-labels on detector training. Specially, RST is formulated as a loss minimization problem for object detection. The experimental results based on the domain adaptation from optical dataset to SAR dataset demonstrate that our approach achieves superior SAR ship detection performance with unlabeled SAR images.

Similar Papers
  • PDF
  • Research Article
  • Citations61

Improved Ship Detection Algorithm Based on YOLOX for SAR Outline Enhancement Image

  • Aug 20, 2022
  • Remote Sensing
  • Sen Li +2
  • Research Article

ESENet: an efficient lightweight network with entropy-guided pooling for SAR ship detection

  • Feb 20, 2026
  • Measurement Science and Technology
  • Yang Cai +10
  • Research Article
  • Citations1

SAR Ship Detection Based on Deep Domain Adaptation with Limited Samples

  • Jan 01, 2023
  • Procedia Computer Science
  • Shangyi Liu +5
  • PDF
  • Research Article
  • Citations283

LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images

  • Sep 15, 2020
  • Remote Sensing
  • Tianwen Zhang +10
  • Research Article
  • Citations12

Despeckling Representation for Data-Efficient SAR Ship Detection

  • Jan 01, 2025
  • IEEE Geoscience and Remote Sensing Letters
  • Ruikang Hu +3
  • PDF
  • Research Article
  • Citations14

LssDet: A Lightweight Deep Learning Detector for SAR Ship Detection in High-Resolution SAR Images

  • Oct 14, 2022
  • Remote Sensing
  • Guoxu Yan +4
  • PDF
  • Research Article
  • Citations14

Soft Thresholding Attention Network for Adaptive Feature Denoising in SAR Ship Detection

  • Jan 01, 2021
  • IEEE Access
  • Rui Wang +5
  • PDF
  • Research Article
  • Citations15

Multi-Size Convolution and Learning Deep Network for SAR Ship Detection From Scratch

  • Jan 01, 2020
  • IEEE Access
  • Long Han +4
  • Research Article
  • Citations377

Squeeze and Excitation Rank Faster R-CNN for Ship Detection in SAR Images

  • May 01, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Zhao Lin +3
  • Research Article
  • Citations61

Frequency-Adaptive Learning for SAR Ship Detection in Clutter Scenes

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Linping Zhang +5
  • Research Article
  • Citations7

Multi-Domain Joint Synthetic Aperture Radar Ship Detection Method Integrating Complex Information with Deep Learning

  • Sep 24, 2024
  • Remote Sensing
  • Chaoyang Tian +4
  • Research Article
  • Citations34

Semisupervised SAR Ship Detection Network via Scene Characteristic Learning

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yuang Du +3
  • Research Article
  • Citations9

FIAD net: a Fast SAR ship detection network based on feature integration attention and self-supervised learning

  • Feb 16, 2022
  • International Journal of Remote Sensing
  • Deyi Wang +2
  • PDF
  • Research Article
  • Citations13

A Spatial Cross-Scale Attention Network and Global Average Accuracy Loss for SAR Ship Detection

  • Jan 06, 2023
  • Remote Sensing
  • Lili Zhang +4
  • Research Article
  • Citations20

Inshore Ship Detection Based on Multi-Modality Saliency for Synthetic Aperture Radar Images

  • Aug 04, 2023
  • Remote Sensing
  • Zhe Chen +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.