In recent years, a large number of meta-learning methods have been proposed to address few-shot learning problems and have shown superior performance. However, the explicit prior knowledge (e.g., concept graph) and weakly-supervised information are rarely explored in existing methods, which are usually free or cheap to collect. In this paper, we introduce a concept graph for the weakly-supervised few-shot learning, and propose a novel meta-learning framework, namely, MetaConcept. Our key idea is to learn a universal meta-learner inferring any-level classifier, so as to boost the classification performance of meta-learning on the novel classes. Specifically, we firstly propose a novel regularization with multi-level conceptual abstraction to train a universal meta-learner to infer not only an entity classifier but also a concept classifier at different levels via the concept graph (i.e., learn to abstract). Then, we propose a meta concept inference network as the universal meta-learner for the base learner, aiming to quickly adapt to a novel task by the joint inference of the abstract concepts and a few annotated samples. We have conducted extensive experiments on two weakly-supervised few-shot learning benchmarks, namely, WS-ImageNet-Pure and WS-ImageNet-Mix. Our experimental results show that (1) the proposed MetaConcept outperforms state-of-the-art methods with an improvement of 2% to 6% in classification accuracy; (2) the proposed MetaConcept is able to yield a good performance though merely training with weakly-labeled datasets.

近年来，已经提出了许多元学习方法来解决少发的学习问题并显示出优异的性能。但是，在现有的方法中，很少会探究显式的先验知识（例如，概念图）和弱监督的信息，这些方法通常免费或廉价地收集。在本文中，我们为弱监督的几次镜头学习引入了一个概念图，并提出了一种新颖的元学习框架，即MetaConcept。我们的关键思想是学习一个可以推导任意级别分类器的通用元学习器，从而提高新型类上元学习的分类性能。具体来说，我们首先提出一种具有多层次概念抽象的新颖正则化方法，以训练通用元学习者不仅可以通过概念图（例如，学习抽象）来推断实体分类器，而且可以推断不同级别的概念分类器。然后，我们提出了一个元概念推理网络，作为基础学习者的通用元学习器，旨在通过抽象概念和一些带注释的样本的联合推理，快速适应新任务。我们已经在两个弱监督的少镜头学习基准上进行了广泛的实验，这两个标准分别是WS-ImageNet-Pure和WS-ImageNet-Mix。我们的实验结果表明：（1）提出的MetaConcept优于最新方法，分类准确率提高了2％至6％；