BriefGPT.xyz
May, 2023
元-DM：扩散模型在小样本学习上的应用
Meta-DM: Applications of Diffusion Models on Few-Shot Learning
HTML
PDF
Wentao Hu, Xiurong Jiang, Jiarun Liu, Yuqi Yang, Hui Tian
TL;DR
本文提出基于扩散模型的通用数据处理模块Meta-DM，该模块可以简单、高效地与现有的Few-Shot Learning方法集成，能在监督和非监督设置下显著提高性能，实验结果表明Meta-DM与某些方法的组合能达到最先进的结果。
Abstract
In the field of
few-shot learning
(FSL), extensive research has focused on improving network structures and training strategies. However, the role of
data processing
modules has not been fully explored. Therefore
→