用原型匹配提升少样本目标检测性能，避免误检和偏差。
Prototype-Driven Adaptation for Few-Shot Object Detection
- 引入原型驱动的度量头，提供与线性分类器互补的判断依据。
- 在少量新类别样本下显著提升检测准确率，对基础类别影响极小。
- 轻量设计适合部署，特别适合资源受限场景下的少样本学习。
少样本目标检测（FSOD）在仅有少量新类别样本时，常因基础类别偏差和校准不稳定而表现不佳。本文提出原型驱动对齐（PDA），一种适用于DeFRCN的轻量级、可插拔度量头，通过原型提供“第二意见”以补充线性分类器。PDA在可学习的身份初始化投影空间中维护仅支持集的原型，并可选地应用原型条件的RoI对齐，以减少几何不匹配。微调阶段，原型通过标注前景RoI的指数移动平均（EMA）更新，无需引入类特定参数；推理时冻结原型以保证严格协议合规。PDA采用最佳K匹配策略捕捉类内多模态特征，并通过温度缩放融合度量相似性与检测器置信度。在VOC FSOD和GFSOD基准测试中，PDA持续提升新类别性能，对基础类别影响微乎其微，计算开销几乎可忽略。实验验证了其有效性与泛化能力。
原文摘要 · Abstract (English)
Few-shot object detection (FSOD) often suffers from base-class bias and unstable calibration when only a few novel samples are available. We propose Prototype-Driven Alignment (PDA), a lightweight, plug-in metric head for DeFRCN that provides a prototype-based "second opinion" complementary to the linear classifier. PDA maintains support-only prototypes in a learnable identity-initialized projection space and optionally applies prototype-conditioned RoI alignment to reduce geometric mismatch. During fine-tuning, prototypes can be adapted via exponential moving average(EMA) updates on labeled foreground RoIs-without introducing class-specific parameters-and are frozen at inference to ensure strict protocol compliance. PDA employs a best-of-K matching scheme to capture intra-class multi-modality and temperature-scaled fusion to combine metric similarities with detector logits. Experiments on VOC FSOD and GFSOD benchmarks show that PDA consistently improves novel-class performance with minimal impact on base classes and negligible computational overhead.
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。