通过目标过采样增强基础模型以应对不平衡SAR船舶分类
Enhancing Foundation Models for Imbalanced SAR Ship Classification via Targeted Oversampling
浏览论文内容
中文总结 AI 辅助
针对SAR船舶分类中的长尾不平衡问题，本文在冻结骨干的协议下，对DOFA和SAR-JEPA在嵌入空间对少数类应用过采样，显著提升Macro-F1，并提供了可复现代码。
中文摘要 AI 辅助
遥感基础模型为SAR图像提供了强大的表示能力，但其在严重长尾类别不平衡下的行为仍未得到充分表征。我们在不平衡的OpenSARShip数据集上对DOFA和SAR-JEPA进行了基准测试，并在保持骨干网络冻结的固定、训练高效的协议下，将它们与ImageNet预训练的基线模型进行比较。为在不进行微调的情况下缓解不平衡，我们在嵌入空间中仅对少数类别应用四种过采样方法，并在增强的嵌入上训练轻量级分类头。对于这两种基础模型，过采样相对于各自的基线提高了Macro-F1和测试准确率，其中DOFA使用ADASYN时Macro-F1增益最大（从34.39提升到38.56），SAR-JEPA使用SVM-SMOTE时增益最大（从25.89提升到32.30）。我们还报告了类别级行为，表明总体改进可能与特定稀有类别的持续失败并存。我们提供了用于嵌入提取和可复现多种子评估的代码，以支持在免费级硬件上进行快速实验。
英文摘要
Remote-sensing foundation models offer strong representations for SAR imagery, but their behavior under severe long-tail class imbalance is still not well characterized. We benchmark DOFA and SAR-JEPA on the imbalanced OpenSARShip dataset and compare them with ImageNet-pretrained baselines under a fixed, training-efficient protocol that keeps the backbone frozen. To mitigate imbalance without fine-tuning, we apply four oversampling methods in embedding space exclusively to minority classes and train a lightweight classifier head on the augmented embeddings. Across both foundation models, oversampling improves Macro-F1 and test accuracy relative to their respective baselines, with the largest Macro-F1 gains observed for DOFA using ADASYN (34.39 to 38.56) and for SAR-JEPA using SVM-SMOTE (25.89 to 32.30). We also report class-wise behavior, showing that aggregate improvements can coexist with persistent failures on specific rare classes. Code for embedding extraction and reproducible multi-seed evaluation is provided to support rapid experimentation on free-tier hardware.
