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

TL;DR

This paper introduces a transfer-based few-shot learning method that preprocesses feature vectors to Gaussian-like distributions and applies an optimal-transport inspired algorithm, achieving state-of-the-art results across multiple vision benchmarks.

Contribution

It proposes a novel two-step transfer-based approach involving feature preprocessing and optimal transport, improving few-shot classification performance.

Findings

Achieves state-of-the-art accuracy on vision benchmarks.

Effective across various datasets and backbone architectures.

Enhances feature distribution to Gaussian-like for better transfer learning.

Abstract

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.