Scholarlink

<p>In recent years, the heterogeneous SAR image classification task of “training on simulated data and testing on measured data” has garnered increasing attention in the field of Synthetic Aperture Radar Automatic Target Recognition (SAR-ATR). Although current mainstream domain adaptation methods have made significant breakthroughs in addressing domain shift problems, the escalating model complexity and task complexity have constrained their deployment in real-world applications. To tackle this challenge, this paper proposes a domain adaptation framework based on linear-kernel Maximum Mean Discrepancy (MMD), integrated with a near-zero-cost pseudo-label denoising technique leveraging deep feature clustering. Our method completely eliminates the need for data augmentation and handcrafted feature design, achieving end-to-end pseudo-label self-training. Competitive performance is demonstrated across three typical scenarios in the SAMPLE dataset, with the highest accuracy of 98.65% achieved in Scenario III. The relevant code is available at: <a href="https://github.com/TheGreatTreatsby/SAMPLE_MMD">https://github.com/TheGreatTreatsby/SAMPLE_MMD</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Domain Adaptation with Deep Feature Clustering for Pseudo-Label Denoising in Heterogeneous SAR Image Classification

  • 期刊论文

  • 发表日期：

    2025年7月9日

查看全文
  • Sheng-Jie Luo,
  • Zhi-Gang Liu,
  • Xi-Hai Li,
  • Yi-Ting Wang,
  • Xiao-Niu Zeng,
  • Zhi-Hao Zheng,
  • Heng Li

摘要

In recent years, the heterogeneous SAR image classification task of “training on simulated data and testing on measured data” has garnered increasing attention in the field of Synthetic Aperture Radar Automatic Target Recognition (SAR-ATR). Although current mainstream domain adaptation methods have made significant breakthroughs in addressing domain shift problems, the escalating model complexity and task complexity have constrained their deployment in real-world applications. To tackle this challenge, this paper proposes a domain adaptation framework based on linear-kernel Maximum Mean Discrepancy (MMD), integrated with a near-zero-cost pseudo-label denoising technique leveraging deep feature clustering. Our method completely eliminates the need for data augmentation and handcrafted feature design, achieving end-to-end pseudo-label self-training. Competitive performance is demonstrated across three typical scenarios in the SAMPLE dataset, with the highest accuracy of 98.65% achieved in Scenario III. The relevant code is available at: https://github.com/TheGreatTreatsby/SAMPLE_MMD.