• Home
  • Search
  • Classification of Large-Scale High-Resolution SAR Images With Deep Transfer Learning
  • Open Access IconOpen Access
  • Cite Icon131
  • https://doi.org/10.1109/lgrs.2020.2965558Copy DOI Icon

Classification of Large-Scale High-Resolution SAR Images With Deep Transfer Learning

Show More
  • Abstract
  • Highlights & Summary
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The classification of large-scale high-resolution SAR land cover images acquired by satellites is a challenging task, facing several difficulties such as semantic annotation with expertise, changing data characteristics due to varying imaging parameters or regional target area differences, and complex scattering mechanisms being different from optical imaging. Given a large-scale SAR land cover dataset collected from TerraSAR-X images with a hierarchical three-level annotation of 150 categories and comprising more than 100,000 patches, three main challenges in automatically interpreting SAR images of highly imbalanced classes, geographic diversity, and label noise are addressed. In this letter, a deep transfer learning method is proposed based on a similarly annotated optical land cover dataset (NWPU-RESISC45). Besides, a top-2 smooth loss function with cost-sensitive parameters was introduced to tackle the label noise and imbalanced classes' problems. The proposed method shows high efficiency in transferring information from a similarly annotated remote sensing dataset, a robust performance on highly imbalanced classes, and is alleviating the over-fitting problem caused by label noise. What's more, the learned deep model has a good generalization for other SAR-specific tasks, such as MSTAR target recognition with a state-of-the-art classification accuracy of 99.46%.

Similar Papers
  • PDF
  • Research Article
  • Citations630

A Review of Deep Transfer Learning and Recent Advancements

  • Mar 14, 2023
  • Technologies
  • Mohammadreza Iman +2
  • PDF
  • Research Article
  • Citations76

A new automatic bearing fault size diagnosis using time-frequency images of CWT and deep transfer learning methods

  • Jul 01, 2022
  • Turkish Journal of Electrical Engineering and Computer Sciences
  • Yilmaz Kaya +2
  • Research Article
  • Citations11

A bidirectional domain separation adversarial network based transfer learning method for near-infrared spectra

  • Aug 26, 2024
  • Engineering Applications of Artificial Intelligence
  • Zheyu Zhang +6
  • PDF
  • Research Article
  • Citations2

Enhanced Sequence-to-Sequence Deep Transfer Learning for Day-Ahead Electricity Load Forecasting

  • May 20, 2024
  • Electronics
  • Vasileios Laitsos +4
  • Book Chapter
  • Citations5

Diabetic Retinopathy Detection with Deep Transfer Learning Methods

  • Aug 24, 2021
  • Gökalp Çinarer +1
  • Book Chapter
  • Citations3

Deep Transfer Learning Approach for Obstructive Sleep Apnea Classification with Photoplethysmography Signal

  • Jan 12, 2023
  • Frontiers in artificial intelligence and applications
  • E Smily Jeya Jothi +2
  • PDF
  • Research Article
  • Citations79

Hyperspectral Imaging Combined With Deep Transfer Learning for Rice Disease Detection

  • Sep 29, 2021
  • Frontiers in Plant Science
  • Lei Feng +3
  • Research Article
  • Citations102

A fault diagnosis method of bearings based on deep transfer learning

  • Sep 23, 2022
  • Simulation Modelling Practice and Theory
  • Min Huang +3
  • Conference Article
  • Citations119

Deep Transfer Learning for Person Re-Identification

  • Sep 01, 2018
  • Haoran Chen +6
  • Research Article
  • Citations476

Deep Transfer Learning for Bearing Fault Diagnosis: A Systematic Review Since 2016

  • Jan 01, 2023
  • IEEE Transactions on Instrumentation and Measurement
  • Xiaohan Chen +5
  • PDF
  • Research Article
  • Citations9

A Scalable High-Performance Unsupervised System for Producing Large-Scale HR Land Cover Maps: The Italian Country Case Study

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Claudia Paris +2
  • Research Article
  • Citations1080

A New Deep Transfer Learning Based on Sparse Auto-Encoder for Fault Diagnosis

  • Jan 01, 2019
  • IEEE Transactions on Systems, Man, and Cybernetics: Systems
  • Long Wen +2
  • Research Article
  • Citations3

StitchingNet and deep transfer learning method for sewing stitch defect detection

  • Mar 29, 2025
  • Journal of Computational Design and Engineering
  • Woo-Kyun Jung +3
  • Research Article
  • Citations11

Gradient-aware learning for joint biases: Label noise and class imbalance

  • Dec 18, 2023
  • Neural Networks
  • Shichuan Zhang +4
  • Research Article
  • Citations37

Addressing data scarcity in protein fitness landscape analysis: A study on semi-supervised and deep transfer learning techniques

  • Sep 22, 2023
  • Information Fusion
  • José A Barbero-Aparicio +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.