Leveraging the Feature Distribution in Transfer-Based Few-Shot Learning

Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, methods have been proposed to solve few-shot classification, among which transfer-based methods have consistently 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. 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.