Few-shot learning aims to learn classification with only a few training examples per class. The metric-based approaches aim to learn a set of embedding functions, so that when represented in this embedding, images are easy to recognize. For metric-based few-shot learning, how to get the class feature representation under a few support samples and what metric to use are important. We propose a multiclass triplet metric-learning network combined with a simple foreground–background feature mixing block. With the foreground–background feature mixing block, we “hallucinate” the information from few support examples to get conceptual representation of classes, which is effective to promote few-shot learning. Furthermore, using the multiclass triplet loss, it learns a feature embedding function that could bring similar samples close to each other and keep samples of different classes far apart. Our proposed network is trained in an end-to-end manner from scratch, so as to learn a good embedding function, conceptual representation of classes, and a nonlinear metric simultaneously. Experimental results on the challenging datasets show that our method with Conv-64F feature extracting block is competitive and effective compared to the metric-based baselines with Conv-64F.

中文翻译：

---

多级三元组度量学习网络与功能混合模块相结合，可进行少量镜头学习

很少有的学习旨在通过每个班级仅提供几个训练示例来学习分类。基于度量的方法旨在学习一组嵌入功能，以便在此嵌入中表示时，易于识别图像。对于基于度量的快速学习，如何在一些支持示例下获取类特征表示以及使用哪种度量很重要。我们提出了结合简单的前景-背景特征混合模块的多类三元组度量学习网络。使用前景-背景特征混合块，我们可以“半透明”一些支持示例中的信息，以获得类的概念表示，这对于促进少量学习是有效的。此外，使用多类三元组损失，它学习了一种特征嵌入功能，该功能可以使相似的样本彼此靠近并使不同类别的样本保持较远的距离。我们提出的网络从头到尾进行了端到端的培训，以便同时学习良好的嵌入功能，类的概念表示和非线性度量。在具有挑战性的数据集上的实验结果表明，与使用Conv-64F的基于度量的基准相比，使用Conv-64F特征提取模块的方法具有竞争力和有效性。