论文标题
IPNET：有影响力的原型网络，用于少数拍摄学习
IPNET:Influential Prototypical Networks for Few Shot Learning
论文作者
论文摘要
原型网络（PN）是一个简单而有效的射击学习策略。这是一种基于公制的元学习技术，通过计算欧几里得距离到每个类的原型表示，可以执行分类。常规的PN属性对所有样品都具有同等的重要性，并通过简单地平均属于每个类的支持样品嵌入来生成原型。在这项工作中，我们提出了一种新颖的PN版本，该版本将权重归因于对应于其对支持样本分布的影响的样品。样品的影响力是根据样品分布的平均嵌入（包括样本和排除样品的平均嵌入）之间的最大平均差异（MMD）计算的。此外，在没有该样品的情况下，使用MMD根据分布的变化来测量样品的影响因子。
Prototypical network (PN) is a simple yet effective few shot learning strategy. It is a metric-based meta-learning technique where classification is performed by computing Euclidean distances to prototypical representations of each class. Conventional PN attributes equal importance to all samples and generates prototypes by simply averaging the support sample embeddings belonging to each class. In this work, we propose a novel version of PN that attributes weights to support samples corresponding to their influence on the support sample distribution. Influence weights of samples are calculated based on maximum mean discrepancy (MMD) between the mean embeddings of sample distributions including and excluding the sample. Further, the influence factor of a sample is measured using MMD based on the shift in the distribution in the absence of that sample.
