Prototype is widely used to represent internal structure of category for few-shot learning, which was proposed as a simple inductive bias to address the issue of overfitting. However, since prototype representation is normally averaged from individual samples, it cannot flexibly adjust the retention ability of sample differences that may leads to underfitting in some cases of sample distribution. To address this problem, in this work, we propose Shrinkage Exemplar Networks (SENet) for few-shot classification. SENet balances the prototype representations (high-bias, low-variance) and example representations (low-bias, high-variance) using a shrinkage estimator, where the categories are represented by the embedings of samples that shrink to their mean via spectral filtering. Furthermore, a shrinkage exemplar loss is proposed to replace the widely used cross entropy loss for capturing the information of individual shrinkage samples. Several experiments were conducted on miniImageNet, tiered-ImageNet and CIFAR-FS datasets. We demonstrate that our proposed model is superior to the example model and the prototype model for some tasks.

翻译：原型（prototype）被广泛用于表征小样本学习中类别的内部结构，作为一种简单的归纳偏置以解决过拟合问题。然而，由于原型表示通常是对单个样本进行平均得到，无法灵活调节对样本差异的保留能力，这可能导致在某些样本分布情况下出现欠拟合。为解决该问题，本文提出收缩样本网络（Shrinkage Exemplar Networks，SENet）用于小样本分类。SENet通过收缩估计器平衡原型表示（高偏差、低方差）与样本表示（低偏差、高方差），其中类别由经过谱滤波收缩至均值的样本嵌入表示。此外，我们提出收缩样本损失函数替代广泛使用的交叉熵损失，以捕获单个收缩样本的信息。在miniImageNet、tiered-ImageNet和CIFAR-FS数据集上进行了多项实验，结果表明本文提出的模型在某些任务上优于样本模型和原型模型。