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.
翻译:Protomid网络(PN)是一个简单而有效的少许简单学习策略,是一种基于标准的元学习技术,其分类方法是通过计算Euclidean距离到每个类的原型表示方式进行分类。常规PN对所有样本都具有同等重要性,通过仅仅平均平均每个类的辅助样本嵌入生成原型。在这项工作中,我们提出了一个新型的PN版本,根据样本对支持样本分布的影响,给样本配置加权以支持样本。根据样本分布中包括和排除样本在内的平均嵌入之间的最大平均差异(MMD)计算样本的重量。此外,根据在没有样本的情况下分布的变化,通过MMD测量样本的影响系数。