Few-shot learning aims at leveraging knowledge learned by one or more deep
learning models, in order to obtain good classification performance on new
problems, where only a few labeled samples per class are available. Recent
years have seen a fair number of works in the field, introducing methods with
numerous ingredients. A frequent problem, though, is the use of suboptimally
trained models to extract knowledge, leading to interrogations on whether
proposed approaches bring gains compared to using better initial models without
the introduced ingredients. In this work, we propose a simple methodology, that
reaches or even beats state of the art performance on multiple standardized
benchmarks of the field, while adding almost no hyperparameters or parameters
to those used for training the initial deep learning models on the generic
dataset. This methodology offers a new baseline on which to propose (and fairly
compare) new techniques or adapt existing ones.

本文提出了一种简单的方法，其几乎没有超参数或参数，并达到或甚至超过领域多个标准基准测试的性能，提供了一个新的基准，可以提出（并公平比较）新技术或改进现有方法。