论文标题
简单：合奏增强镜头Y形学习：最先进的几个分类与简单的成分
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
论文作者
论文摘要
为了利用一个或多个深度学习模型所学的知识，几乎没有学习的目标，以便在新问题上获得良好的分类性能，在新问题上，每个课程只有几个标签的样本。近年来，该领域有很多作品，引入了许多成分的方法。但是，一个常见的问题是使用次优训练的模型来提取知识，从而审问了提议的方法是否带来了与使用更好的初始模型相比而没有引入的成分。在这项工作中，我们提出了一种简单的方法，该方法可以在该领域的多个标准化基准上达到甚至击败最先进的性能，同时几乎没有在通用数据集中训练初始深度学习模型的那些几乎没有超参数或参数。该方法提供了一个新的基线，可以在其上提出（并相当比较）新技术或调整现有技术。
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.
