Few-shot object detection (FSOD) aims to achieve object detection only using a few novel class training data. Most of the existing methods usually adopt a transfer-learning strategy to construct the novel class distribution by transferring the base class knowledge. However, this direct way easily results in confusion between the novel class and other similar categories in the decision space. To address the problem, we propose generating local reverse samples (LRSamples) in Prototype Reference Frames to adaptively adjust the center position and boundary range of the novel class distribution to learn more discriminative novel class samples for FSOD. Firstly, we propose a Center Calibration Variance Augmentation (CCVA) module, which contains the selection rule of LRSamples, the generator of LRSamples, and augmentation on the calibrated distribution centers. Specifically, we design an intra-class feature converter (IFC) as the generator of CCVA to learn the selecting rule. By transferring the knowledge of IFC from the base training to fine-tuning, the IFC generates plentiful novel samples to calibrate the novel class distribution. Moreover, we propose a Feature Density Boundary Optimization (FDBO) module to adaptively adjust the importance of samples depending on their distance from the decision boundary. It can emphasize the importance of the high-density area of the similar class (closer decision boundary area) and reduce the weight of the low-density area of the similar class (farther decision boundary area), thus optimizing a clearer decision boundary for each category. We conduct extensive experiments to demonstrate the effectiveness of our proposed method. Our method achieves consistent improvement on the Pascal VOC and MS COCO datasets based on DeFRCN and MFDC baselines.

翻译：小样本目标检测（FSOD）旨在仅使用少量新类训练数据实现目标检测。现有方法通常采用迁移学习策略，通过迁移基类知识构建新类分布。然而，这种直接方式容易导致决策空间中新类与其他相似类别之间的混淆。为解决该问题，我们提出在原型参考框架中生成局部反向样本（LRSamples），自适应调整新类分布的中心位置和边界范围，为FSOD学习更具判别性的新类样本。首先，我们提出中心校准方差增强（CCVA）模块，包含LRSamples的选择规则、LRSamples生成器以及校准分布中心的增强机制。具体而言，我们设计类内特征转换器（IFC）作为CCVA的生成器来学习选择规则。通过将IFC的知识从基类训练迁移至微调阶段，IFC生成大量新样本以校准新类分布。此外，我们提出特征密度边界优化（FDBO）模块，根据样本与决策边界的距离自适应调整其重要性。该模块可强调相似类高密度区域（更接近决策边界区域）的重要性，同时降低相似类低密度区域（远离决策边界区域）的权重，从而为每个类别优化更清晰的决策边界。我们通过大量实验验证了所提方法的有效性。基于DeFRCN和MFDC基线，我们的方法在Pascal VOC和MS COCO数据集上均实现了一致性提升。