Leveraging the Feature Distribution in Transfer-Based Few-Shot Learning - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

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

Résumé

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.

Dates et versions

hal-03675135 , version 1 (22-05-2022)

Identifiants

Citer

Vincent Gripon, Yuqing Hu, Stéphane Pateux. Leveraging the Feature Distribution in Transfer-Based Few-Shot Learning. ICANN 2021: 30th International Conference on Artificial Neural Networks, Sep 2021, Bratislava, Slovakia. pp.487-499, ⟨10.1007/978-3-030-86340-1_39⟩. ⟨hal-03675135⟩
56 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More