论文标题
利用基于转移的几次学习中的特征分布
Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
论文作者
论文摘要
由于使用了很少的标记样品引起的不确定性，因此很少有射击分类是一个具有挑战性的问题。在过去的几年中，已经提出了许多方法来解决少量分类，其中基于转移的方法已证明可以实现最佳性能。遵循这种静脉，在本文中，我们提出了一种基于转移的新方法，该方法基于两个连续的步骤：1）预处理特征向量，以使它们更接近类似高斯的分布，以及2）使用最佳传播的算法利用此预处理（在传播设置的情况下）。使用标准化的视觉基准测试，我们证明了提出的方法可以通过各种数据集，骨干架构和少量设置来实现最先进的精度。
Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed to solve few-shot classification, among which transfer-based methods have proved to achieve the best performance. Following this vein, in this paper we propose a novel transfer-based method that builds on two successive steps: 1) preprocessing the feature vectors so that they become closer to Gaussian-like distributions, and 2) leveraging this preprocessing using an optimal-transport inspired algorithm (in the case of transductive settings). Using standardized vision benchmarks, we prove the ability of the proposed methodology to achieve state-of-the-art accuracy with various datasets, backbone architectures and few-shot settings.
