通过形状空间的测地线曲线增强特征，解决数据少时的分类难题。
FAAGC: Feature Augmentation on Adaptive Geodesic Curve Based on the shape space theory
- 在预形状空间中构建类间测地线弧，沿路径采样增广特征。
- 在数据稀缺下提升分类准确率，对多种特征类型均有效。
- 适合小样本学习与特征多样性不足场景，可推广至多领域。
深度学习模型已在多个领域广泛应用，但许多场景仍受限于数据稀少的问题。本文提出一种基于形状空间理论的自适应测地线曲线特征增广方法（FAAGC），在预形状空间中增加数据。在预形状空间中，相同形状的对象位于大圆上。因此，将深度模型的表示投影到预形状空间，并为每类构造一条测地线曲线，即大圆的一段弧。通过沿这些测地线路径采样实现特征增广。大量实验表明，该方法在数据稀缺条件下显著提升分类准确率，且对多种特征类型具有良好泛化能力。
原文摘要 · Abstract (English)
Deep learning models have been widely applied across various domains and industries. However, many fields still face challenges due to limited and insufficient data. This paper proposes a Feature Augmentation on Adaptive Geodesic Curve (FAAGC) method in the pre-shape space to increase data. In the pre-shape space, objects with identical shapes lie on a great circle. Thus, we project deep model representations into the pre-shape space and construct a geodesic curve, i.e., an arc of a great circle, for each class. Feature augmentation is then performed by sampling along these geodesic paths. Extensive experiments demonstrate that FAAGC improves classification accuracy under data-scarce conditions and generalizes well across various feature types.
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。