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

Code

• github.com/yhu01/PT-MAP
  OfficialIn paperpytorch★ 215
• github.com/sicara/easy-few-shot-learning
  pytorch★ 1,301
• github.com/yhu01/bms
  pytorch★ 39
• github.com/xiangyu8/PT-MAP-sf
  pytorch★ 24
• github.com/mbonto/fewshot_neuroimaging_classification
  pytorch★ 10
• github.com/allenhaozhu/ease
  pytorch★ 10

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.

Tasks

Benchmark Results

Reproductions