论文标题
基于图的特征向量的插值，以精确几次分类
Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification
论文作者
论文摘要
在几个射击分类中，目的是学习能够仅使用少数标记示例来区分类的模型。在这种情况下，作品提出了介绍旨在利用同时处理的其他样本中包含的信息的图形神经网络（GNN），通常称为文献中通常称为转导设置。这些GNN与骨干特征提取器一起训练。在本文中，我们提出了一种新方法，该方法仅依赖于图形，而仅用于插值特征向量，从而导致了带驱动性的学习设置，而没有其他参数可以训练。因此，我们提出的方法利用了两个级别的信息：a）在通用数据集中获得的传输特征，b）从其他样本中获得的转导信息。使用标准的少量视觉分类数据集，我们证明了与其他作品相比，它带来了可观的增长能力。
In few-shot classification, the aim is to learn models able to discriminate classes using only a small number of labeled examples. In this context, works have proposed to introduce Graph Neural Networks (GNNs) aiming at exploiting the information contained in other samples treated concurrently, what is commonly referred to as the transductive setting in the literature. These GNNs are trained all together with a backbone feature extractor. In this paper, we propose a new method that relies on graphs only to interpolate feature vectors instead, resulting in a transductive learning setting with no additional parameters to train. Our proposed method thus exploits two levels of information: a) transfer features obtained on generic datasets, b) transductive information obtained from other samples to be classified. Using standard few-shot vision classification datasets, we demonstrate its ability to bring significant gains compared to other works.
