论文标题
LFD-Protonet：基于本地Fisher判别分析的原型网络，用于几次学习
LFD-ProtoNet: Prototypical Network Based on Local Fisher Discriminant Analysis for Few-shot Learning
论文作者
论文摘要
原型网络（Protonet）是几个弹奏学习框架，使用每个类的原型表示距离进行度量学习和分类。由于它易于实施，高度扩展并且在实验中表现良好，因此最近引起了广泛的关注。但是，它仅考虑支持向量的平均值作为原型，因此当支持集具有较高的方差时，其性能差。在本文中，我们建议将质子与局部费舍尔判别分析相结合，以减少当地的课堂协方差，并增加支持集的局部阶层之间的协方差。我们通过从理论上提供了预期的风险结合，并在经验上证明了其在迷你象征和tieredimagenet上的出色分类准确性，从而证明了所提出的方法的实用性。
The prototypical network (ProtoNet) is a few-shot learning framework that performs metric learning and classification using the distance to prototype representations of each class. It has attracted a great deal of attention recently since it is simple to implement, highly extensible, and performs well in experiments. However, it only takes into account the mean of the support vectors as prototypes and thus it performs poorly when the support set has high variance. In this paper, we propose to combine ProtoNet with local Fisher discriminant analysis to reduce the local within-class covariance and increase the local between-class covariance of the support set. We show the usefulness of the proposed method by theoretically providing an expected risk bound and empirically demonstrating its superior classification accuracy on miniImageNet and tieredImageNet.
