针对雷达船舰分类中的类别不平衡问题，提出特征空间过采样新方法。
Feature-Space Oversampling for Addressing Class Imbalance in SAR Ship Classification
- 在特征空间中设计两类过采样算法，提升少数类样本表达能力。
- 在两个公开数据集上平均F1分数提升4.44%至8.82%。
- 适用于遥感图像中长尾分布的少样本类别识别任务。
SAR船舰分类面临长尾数据分布的挑战，导致少数类难以准确识别。传统过采样方法在光学图像中表现良好，但对SAR数据效果有限。本文评估了特征空间过采样的有效性，提出了受M2m方法启发的两种新算法：M2m$_f$ 和 M2m$_u$。在两个公开数据集OpenSARShip（6类）和FuSARShip（9类）上，结合ViT、VGG16、ResNet50三种主流模型作为特征提取器进行测试。实验表明，所提方法在不同类别规模下均有效，相比原始M2m及基线模型，在FuSARShip上平均F1分数提升8.82%，在OpenSARShip上提升4.44%。
原文摘要 · Abstract (English)
SAR ship classification faces the challenge of long-tailed datasets, which complicates the classification of underrepresented classes. Oversampling methods have proven effective in addressing class imbalance in optical data. In this paper, we evaluated the effect of oversampling in the feature space for SAR ship classification. We propose two novel algorithms inspired by the Major-to-minor (M2m) method M2m$_f$, M2m$_u$. The algorithms are tested on two public datasets, OpenSARShip (6 classes) and FuSARShip (9 classes), using three state-of-the-art models as feature extractors: ViT, VGG16, and ResNet50. Additionally, we also analyzed the impact of oversampling methods on different class sizes. The results demonstrated the effectiveness of our novel methods over the original M2m and baselines, with an average F1-score increase of 8.82% for FuSARShip and 4.44% for OpenSARShip.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。