Few-shot learning (FSL) is popular due to its ability to adapt to novel classes. Compared with inductive few-shot learning, transductive models typically perform better as they leverage all samples of the query set. The two existing classes of methods, prototype-based and graph-based, have the disadvantages of inaccurate prototype estimation and sub-optimal graph construction with kernel functions, respectively. In this paper, we propose a novel prototype-based label propagation to solve these issues. Specifically, our graph construction is based on the relation between prototypes and samples rather than between samples. As prototypes are being updated, the graph changes. We also estimate the label of each prototype instead of considering a prototype be the class centre. On mini-ImageNet, tiered-ImageNet, CIFAR-FS and CUB datasets, we show the proposed method outperforms other state-of-the-art methods in transductive FSL and semi-supervised FSL when some unlabeled data accompanies the novel few-shot task.

翻译：小样本学习因其适应新类别的能力而广受欢迎。与归纳式小样本学习相比，直推式模型通常表现更好，因为它们利用了查询集的所有样本。现有的两类方法——基于原型的方法和基于图的方法——分别存在原型估计不准确以及使用核函数构建次优图的缺点。本文提出了一种新的基于原型的标签传播方法来解决这些问题。具体而言，我们的图构建是基于原型与样本之间的关系，而非样本之间的关系。随着原型的更新，图也会随之变化。我们同时估计每个原型的标签，而非将原型视为类别中心。在mini-ImageNet、tiered-ImageNet、CIFAR-FS和CUB数据集上，我们展示了所提方法在直推式小样本学习以及半监督小样本学习中（当新类小样本任务伴随部分无标签数据时）优于其他最先进方法的表现。