Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning

In many real-life problems, it is difficult to acquire or label large amounts of data, resulting in so-called few-shot learning problems. However, few-shot classification is a challenging problem due to the uncertainty caused by using few labeled samples. In the past few years, many methods have bee...

Полное описание

Библиографические подробности

Главные авторы:	Yuqing Hu, Stéphane Pateux, Vincent Gripon
Формат:	Artigo
Язык:	Inglês
Опубликовано:	MDPI AG 2022-04-01
Серии:	Algorithms
Предметы:	few-shot learning inductive and transductive learning transfer learning optimal transport
Online-ссылка:	https://www.mdpi.com/1999-4893/15/5/147
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!